This paper proposes a cascade deep convolutional neural network to address the loosening detection problem of bolts on axlebox covers.Firstly,an SSD network based on ResNet50 and CBAM module by improving bolt image fe...This paper proposes a cascade deep convolutional neural network to address the loosening detection problem of bolts on axlebox covers.Firstly,an SSD network based on ResNet50 and CBAM module by improving bolt image features is proposed for locating bolts on axlebox covers.And then,theA2-PFN is proposed according to the slender features of the marker lines for extracting more accurate marker lines regions of the bolts.Finally,a rectangular approximationmethod is proposed to regularize themarker line regions asaway tocalculate the angle of themarker line and plot all the angle values into an angle table,according to which the criteria of the angle table can determine whether the bolt with the marker line is in danger of loosening.Meanwhile,our improved algorithm is compared with the pre-improved algorithmin the object localization stage.The results show that our proposed method has a significant improvement in both detection accuracy and detection speed,where ourmAP(IoU=0.75)reaches 0.77 and fps reaches 16.6.And in the saliency detection stage,after qualitative comparison and quantitative comparison,our method significantly outperforms other state-of-the-art methods,where our MAE reaches 0.092,F-measure reaches 0.948 and AUC reaches 0.943.Ultimately,according to the angle table,out of 676 bolt samples,a total of 60 bolts are loose,69 bolts are at risk of loosening,and 547 bolts are tightened.展开更多
Enabling high mobility applications in millimeter wave(mmWave)based systems opens up a slew of new possibilities,including vehicle communi-cations in addition to wireless virtual/augmented reality.The narrow beam usag...Enabling high mobility applications in millimeter wave(mmWave)based systems opens up a slew of new possibilities,including vehicle communi-cations in addition to wireless virtual/augmented reality.The narrow beam usage in addition to the millimeter waves sensitivity might block the coverage along with the reliability of the mobile links.In this research work,the improvement in the quality of experience faced by the user for multimedia-related applications over the millimeter-wave band is investigated.The high attenuation loss in high frequencies is compensated with a massive array structure named Multiple Input and Multiple Output(MIMO)which is utilized in a hyperdense environment called heterogeneous networks(HetNet).The optimization problem which arises while maximizing the Mean Opinion Score(MOS)is analyzed along with the QoE(Quality of Experience)metric by considering the Base Station(BS)powers in addition to the needed Quality of Service(QoS).Most of the approaches related to wireless network communication are not suitable for the millimeter-wave band because of its problems due to high complexity and its dynamic nature.Hence a deep reinforcement learning framework is developed for tackling the same opti-mization problem.In this work,a Fuzzy-based Deep Convolutional Neural Net-work(FDCNN)is proposed in addition to a Deep Reinforcing Learning Framework(DRLF)for extracting the features of highly correlated data.The investigational results prove that the proposed method yields the highest satisfac-tion to the user by increasing the number of antennas in addition with the small-scale antennas at the base stations.The proposed work outperforms in terms of MOS with multiple antennas.展开更多
Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However...Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However,previous methods have several challenges in costly,time-consuming,and unsafety.To address these drawbacks,this paper proposed a digital vision based concrete compressive strength evaluating model using deep convolutional neural network(DCNN).The proposed model presented an alternative approach to evaluating the concrete strength and contributed to improving efficiency and accuracy.The model was developed with 4,000 digital images and 61,996 images extracted from video recordings collected from concrete samples.The experimental results indicated a root mean square error(RMSE)value of 3.56(MPa),demonstrating a strong feasibility that the proposed model can be utilized to predict the concrete strength with digital images of their surfaces and advantages to overcome the previous limitations.This experiment contributed to provide the basis that could be extended to future research with image analysis technique and artificial neural network in the diagnosis of concrete building structures.展开更多
In this study,we examined the efficacy of a deep convolutional neural network(DCNN)in recognizing concrete surface images and predicting the compressive strength of concrete.A digital single-lens reflex(DSLR)camera an...In this study,we examined the efficacy of a deep convolutional neural network(DCNN)in recognizing concrete surface images and predicting the compressive strength of concrete.A digital single-lens reflex(DSLR)camera and microscope were simultaneously used to obtain concrete surface images used as the input data for the DCNN.Thereafter,training,validation,and testing of the DCNNs were performed based on the DSLR camera and microscope image data.Results of the analysis indicated that the DCNN employing DSLR image data achieved a relatively higher accuracy.The accuracy of the DSLR-derived image data was attributed to the relatively wider range of the DSLR camera,which was beneficial for extracting a larger number of features.Moreover,the DSLR camera procured more realistic images than the microscope.Thus,when the compressive strength of concrete was evaluated using the DCNN employing a DSLR camera,time and cost were reduced,whereas the usefulness increased.Furthermore,an indirect comparison of the accuracy of the DCNN with that of existing non-destructive methods for evaluating the strength of concrete proved the reliability of DCNN-derived concrete strength predictions.In addition,it was determined that the DCNN used for concrete strength evaluations in this study can be further expanded to detect and evaluate various deteriorative factors that affect the durability of structures,such as salt damage,carbonation,sulfation,corrosion,and freezing-thawing.展开更多
The novel coronavirus 2019(COVID-19)rapidly spreading around the world and turns into a pandemic situation,consequently,detecting the coronavirus(COVID-19)affected patients are now the most critical task for medical s...The novel coronavirus 2019(COVID-19)rapidly spreading around the world and turns into a pandemic situation,consequently,detecting the coronavirus(COVID-19)affected patients are now the most critical task for medical specialists.The deficiency of medical testing kits leading to huge complexity in detecting COVID-19 patients worldwide,resulting in the number of infected cases is expanding.Therefore,a significant study is necessary about detecting COVID-19 patients using an automated diagnosis method,which hinders the spreading of coronavirus.In this paper,the study suggests a Deep Convolutional Neural Network-based multi-classification framework(COV-MCNet)using eight different pre-trained architectures such as VGG16,VGG19,ResNet50V2,DenseNet201,InceptionV3,MobileNet,InceptionResNetV2,Xception which are trained and tested on the X-ray images of COVID-19,Normal,Viral Pneumonia,and Bacterial Pneumonia.The results from 4-class(Normal vs.COVID-19 vs.Viral Pneumonia vs.Bacterial Pneumonia)demonstrated that the pre-trained model DenseNet201 provides the highest classification performance(accuracy:92.54%,precision:93.05%,recall:92.81%,F1-score:92.83%,specificity:97.47%).Notably,the DenseNet201(4-class classification)pre-trained model in the proposed COV-MCNet framework showed higher accuracy compared to the rest seven models.Important to mention that the proposed COV-MCNet model showed comparatively higher classification accuracy based on the small number of pre-processed datasets that specifies the designed system can produce superior results when more data become available.The proposed multi-classification network(COV-MCNet)significantly speeds up the existing radiology based method which will be helpful for the medical community and clinical specialists to early diagnosis the COVID-19 cases during this pandemic.展开更多
Graph Convolutional Neural Networks(GCNs)have been widely used in various fields due to their powerful capabilities in processing graph-structured data.However,GCNs encounter significant challenges when applied to sca...Graph Convolutional Neural Networks(GCNs)have been widely used in various fields due to their powerful capabilities in processing graph-structured data.However,GCNs encounter significant challenges when applied to scale-free graphs with power-law distributions,resulting in substantial distortions.Moreover,most of the existing GCN models are shallow structures,which restricts their ability to capture dependencies among distant nodes and more refined high-order node features in scale-free graphs with hierarchical structures.To more broadly and precisely apply GCNs to real-world graphs exhibiting scale-free or hierarchical structures and utilize multi-level aggregation of GCNs for capturing high-level information in local representations,we propose the Hyperbolic Deep Graph Convolutional Neural Network(HDGCNN),an end-to-end deep graph representation learning framework that can map scale-free graphs from Euclidean space to hyperbolic space.In HDGCNN,we define the fundamental operations of deep graph convolutional neural networks in hyperbolic space.Additionally,we introduce a hyperbolic feature transformation method based on identity mapping and a dense connection scheme based on a novel non-local message passing framework.In addition,we present a neighborhood aggregation method that combines initial structural featureswith hyperbolic attention coefficients.Through the above methods,HDGCNN effectively leverages both the structural features and node features of graph data,enabling enhanced exploration of non-local structural features and more refined node features in scale-free or hierarchical graphs.Experimental results demonstrate that HDGCNN achieves remarkable performance improvements over state-ofthe-art GCNs in node classification and link prediction tasks,even when utilizing low-dimensional embedding representations.Furthermore,when compared to shallow hyperbolic graph convolutional neural network models,HDGCNN exhibits notable advantages and performance enhancements.展开更多
Watermarking is the advanced technology utilized to secure digital data by integrating ownership or copyright protection.Most of the traditional extracting processes in audio watermarking have some restrictions due to...Watermarking is the advanced technology utilized to secure digital data by integrating ownership or copyright protection.Most of the traditional extracting processes in audio watermarking have some restrictions due to low reliability to various attacks.Hence,a deep learning-based audio watermarking system is proposed in this research to overcome the restriction in the traditional methods.The implication of the research relies on enhancing the performance of the watermarking system using the Discrete Wavelet Transform(DWT)and the optimized deep learning technique.The selection of optimal embedding location is the research contribution that is carried out by the deep convolutional neural network(DCNN).The hyperparameter tuning is performed by the so-called search location optimization,which minimizes the errors in the classifier.The experimental result reveals that the proposed digital audio watermarking system provides better robustness and performance in terms of Bit Error Rate(BER),Mean Square Error(MSE),and Signal-to-noise ratio.The BER,MSE,and SNR of the proposed audio watermarking model without the noise are 0.082,0.099,and 45.363 respectively,which is found to be better performance than the existing watermarking models.展开更多
The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software w...The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software with defects negatively impacts operational costs and finally affects customer satisfaction. Numerous approaches exist to predict software defects. However, the timely and accurate software bugs are the major challenging issues. To improve the timely and accurate software defect prediction, a novel technique called Nonparametric Statistical feature scaled QuAdratic regressive convolution Deep nEural Network (SQADEN) is introduced. The proposed SQADEN technique mainly includes two major processes namely metric or feature selection and classification. First, the SQADEN uses the nonparametric statistical Torgerson–Gower scaling technique for identifying the relevant software metrics by measuring the similarity using the dice coefficient. The feature selection process is used to minimize the time complexity of software fault prediction. With the selected metrics, software fault perdition with the help of the Quadratic Censored regressive convolution deep neural network-based classification. The deep learning classifier analyzes the training and testing samples using the contingency correlation coefficient. The softstep activation function is used to provide the final fault prediction results. To minimize the error, the Nelder–Mead method is applied to solve non-linear least-squares problems. Finally, accurate classification results with a minimum error are obtained at the output layer. Experimental evaluation is carried out with different quantitative metrics such as accuracy, precision, recall, F-measure, and time complexity. The analyzed results demonstrate the superior performance of our proposed SQADEN technique with maximum accuracy, sensitivity and specificity by 3%, 3%, 2% and 3% and minimum time and space by 13% and 15% when compared with the two state-of-the-art methods.展开更多
The automatic individual identification of Amur tigers(Panthera tigris altaica)is important for population monitoring and making effective conservation strategies.Most existing research primarily relies on manual iden...The automatic individual identification of Amur tigers(Panthera tigris altaica)is important for population monitoring and making effective conservation strategies.Most existing research primarily relies on manual identifi-cation,which does not scale well to large datasets.In this paper,the deep convolution neural networks algorithm is constructed to implement the automatic individual identification for large numbers of Amur tiger images.The experimental data were obtained from 40 Amur tigers in Tieling Guaipo Tiger Park,China.The number of images collected from each tiger was approximately 200,and a total of 8277 images were obtained.The experiments were carried out on both the left and right side of body.Our results suggested that the recognition accuracy rate of left and right sides are 90.48%and 93.5%,respectively.The accuracy of our network has achieved the similar level compared to other state of the art networks like LeNet,ResNet34,and ZF_Net.The running time is much shorter than that of other networks.Consequently,this study can provide a new approach on automatic individual identification technology in the case of the Amur tiger.展开更多
Skin lesions are in a category of disease that is both common in humans and a major cause of death.The classification accuracy of skin lesions is a crucial determinant of the success rate of curing lethal diseases.Dee...Skin lesions are in a category of disease that is both common in humans and a major cause of death.The classification accuracy of skin lesions is a crucial determinant of the success rate of curing lethal diseases.Deep Convolutional Neural Networks(CNNs)are now the most prevalent computer algorithms for the purpose of disease classification.As with all algorithms,CNNs are sensitive to noise from imaging devices,which often contaminates the quality of the images that are fed into them.In this paper,a deep CNN(Inception-v3)is used to study the effect of image noise on the classification of skin lesions.Gaussian noise,impulse noise,and noise made up of a compound of the two are added to an image dataset,namely the Dermofit Image Library from the University of Edinburgh.Evaluations,based on t-distributed Stochastic Neighbor Embedding(t-SNE)visualization,Receiver Operating Characteristic(ROC)analysis,and saliency maps,demonstrate the reliability of the Inception-v3 deep CNN in classifying noisy skin lesion images.展开更多
Existing learning-based super-resolution (SR) reconstruction algorithms are mainly designed for single image, which ignore the spatio-temporal relationship between video frames. Aiming at applying the advantages of ...Existing learning-based super-resolution (SR) reconstruction algorithms are mainly designed for single image, which ignore the spatio-temporal relationship between video frames. Aiming at applying the advantages of learning-based algorithms to video SR field, a novel video SR reconstruction algorithm based on deep convolutional neural network (CNN) and spatio-temporal similarity (STCNN-SR) was proposed in this paper. It is a deep learning method for video SR reconstruction, which considers not onlv the mapping relationship among associated low-resolution (LR) and high-resolution (HR) image blocks, but also the spatio-temporal non-local complementary and redundant information between adjacent low-resolution video frames. The reconstruction speed can be improved obviously with the pre-trained end-to-end reconstructed coefficients. Moreover, the performance of video SR will be further improved by the optimization process with spatio-temporal similarity. Experimental results demonstrated that the proposed algorithm achieves a competitive SR quality on both subjective and objective evaluations, when compared to other state-of-the-art algorithms.展开更多
Deformable microcapsules are widely used in industries and also serve as a mechanical model of living biological cells.In this study,we develop a novel method,by integrating a deep convolutional neural network(DCNN)wi...Deformable microcapsules are widely used in industries and also serve as a mechanical model of living biological cells.In this study,we develop a novel method,by integrating a deep convolutional neural network(DCNN)with high-fidelity mechanistic capsule modelling,to identify the membrane constitutive law and estimate associated parameters of a microcapsule from its steady deformed profile in a capillary tube.Compared with conventional inverse methods,the present approach is more accurate and can increase the prediction throughput rate by a few orders of magnitude.It can process capsules with large deformation in inertial flows.Furthermore,the method can predict the capsule membrane shear elasticity,area dilatation modulus and initial inflation from a single steady capsule profile.We explore the mechanism that the DCNN makes decisions by considering its feature maps,and discuss their potential implication on the development of inverse methods.The present method provides a promising tool which may enable high-throughput mechanical characterisation of microcapsules and biological cells in microfluidic flows.展开更多
Since of the scale and the various shapes of down in the image,it is difficult for traditional image recognition method to correctly recognize the type of down image and get the required recognition accuracy,even for ...Since of the scale and the various shapes of down in the image,it is difficult for traditional image recognition method to correctly recognize the type of down image and get the required recognition accuracy,even for the Traditional Convolutional Neural Network(TCNN).To deal with the above problems,a Deep Convolutional Neural Network(DCNN)for down image classification is constructed,and a new weight initialization method is proposed.Firstly,the salient regions of a down image were cut from the image using the visual saliency model.Then,these salient regions of the image were used to train a sparse autoencoder and get a collection of convolutional filters,which accord with the statistical characteristics of dataset.At last,a DCNN with Inception module and its variants was constructed.To improve the recognition accuracy,the depth of the network is deepened.The experiment results indicate that the constructed DCNN increases the recognition accuracy by 2.7% compared to TCNN,when recognizing the down in the images.The convergence rate of the proposed DCNN with the new weight initialization method is improved by 25.5% compared to TCNN.展开更多
In recent years,computer visionfinds wide applications in maritime surveillance with its sophisticated algorithms and advanced architecture.Auto-matic ship detection with computer vision techniques provide an efficien...In recent years,computer visionfinds wide applications in maritime surveillance with its sophisticated algorithms and advanced architecture.Auto-matic ship detection with computer vision techniques provide an efficient means to monitor as well as track ships in water bodies.Waterways being an important medium of transport require continuous monitoring for protection of national security.The remote sensing satellite images of ships in harbours and water bodies are the image data that aid the neural network models to localize ships and to facilitate early identification of possible threats at sea.This paper proposes a deep learning based model capable enough to classify between ships and no-ships as well as to localize ships in the original images using bounding box tech-nique.Furthermore,classified ships are again segmented with deep learning based auto-encoder model.The proposed model,in terms of classification,provides suc-cessful results generating 99.5%and 99.2%validation and training accuracy respectively.The auto-encoder model also produces 85.1%and 84.2%validation and training accuracies.Moreover the IoU metric of the segmented images is found to be of 0.77 value.The experimental results reveal that the model is accu-rate and can be implemented for automatic ship detection in water bodies consid-ering remote sensing satellite images as input to the computer vision system.展开更多
Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly acc...Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.展开更多
Early diagnosis and detection are important tasks in controlling the spread of COVID-19.A number of Deep Learning techniques has been established by researchers to detect the presence of COVID-19 using CT scan images ...Early diagnosis and detection are important tasks in controlling the spread of COVID-19.A number of Deep Learning techniques has been established by researchers to detect the presence of COVID-19 using CT scan images and X-rays.However,these methods suffer from biased results and inaccurate detection of the disease.So,the current research article developed Oppositional-based Chimp Optimization Algorithm and Deep Dense Convolutional Neural Network(OCOA-DDCNN)for COVID-19 prediction using CT images in IoT environment.The proposed methodology works on the basis of two stages such as pre-processing and prediction.Initially,CT scan images generated from prospective COVID-19 are collected from open-source system using IoT devices.The collected images are then preprocessed using Gaussian filter.Gaussian filter can be utilized in the removal of unwanted noise from the collected CT scan images.Afterwards,the preprocessed images are sent to prediction phase.In this phase,Deep Dense Convolutional Neural Network(DDCNN)is applied upon the pre-processed images.The proposed classifier is optimally designed with the consideration of Oppositional-basedChimp Optimization Algorithm(OCOA).This algorithm is utilized in the selection of optimal parameters for the proposed classifier.Finally,the proposed technique is used in the prediction of COVID-19 and classify the results as either COVID-19 or non-COVID-19.The projected method was implemented in MATLAB and the performances were evaluated through statistical measurements.The proposed method was contrasted with conventional techniques such as Convolutional Neural Network-Firefly Algorithm(CNN-FA),Emperor Penguin Optimization(CNN-EPO)respectively.The results established the supremacy of the proposed model.展开更多
The most widely farmed fruit in the world is mango.Both the production and quality of the mangoes are hampered by many diseases.These diseases need to be effectively controlled and mitigated.Therefore,a quick and accu...The most widely farmed fruit in the world is mango.Both the production and quality of the mangoes are hampered by many diseases.These diseases need to be effectively controlled and mitigated.Therefore,a quick and accurate diagnosis of the disorders is essential.Deep convolutional neural networks,renowned for their independence in feature extraction,have established their value in numerous detection and classification tasks.However,it requires large training datasets and several parameters that need careful adjustment.The proposed Modified Dense Convolutional Network(MDCN)provides a successful classification scheme for plant diseases affecting mango leaves.This model employs the strength of pre-trained networks and modifies them for the particular context of mango leaf diseases by incorporating transfer learning techniques.The data loader also builds mini-batches for training the models to reduce training time.Finally,optimization approaches help increase the overall model’s efficiency and lower computing costs.MDCN employed on the MangoLeafBD Dataset consists of a total of 4,000 images.Following the experimental results,the proposed system is compared with existing techniques and it is clear that the proposed algorithm surpasses the existing algorithms by achieving high performance and overall throughput.展开更多
Deep Convolutional Neural Networks(CNNs)have achieved high accuracy in image classification tasks,however,most existing models are trained on high-quality images that are not subject to image degradation.In practice,i...Deep Convolutional Neural Networks(CNNs)have achieved high accuracy in image classification tasks,however,most existing models are trained on high-quality images that are not subject to image degradation.In practice,images are often affected by various types of degradation which can significantly impact the performance of CNNs.In this work,we investigate the influence of image degradation on three typical image classification CNNs and propose a Degradation Type Adaptive Image Classification Model(DTA-ICM)to improve the existing CNNs’classification accuracy on degraded images.The proposed DTA-ICM comprises two key components:a Degradation Type Predictor(DTP)and a Degradation Type Specified Image Classifier(DTS-IC)set,which is trained on existing CNNs for specified types of degradation.The DTP predicts the degradation type of a test image,and the corresponding DTS-IC is then selected to classify the image.We evaluate the performance of both the proposed DTP and the DTA-ICMon the Caltech 101 database.The experimental results demonstrate that the proposed DTP achieves an average accuracy of 99.70%.Moreover,the proposed DTA-ICM,based on AlexNet,VGG19,and ResNet152,exhibits an average accuracy improvement of 20.63%,18.22%,and 12.9%,respectively,compared with the original CNNs in classifying degraded images.It suggests that the proposed DTA-ICM can effectively improve the classification performance of existing CNNs on degraded images,which has important practical implications.展开更多
Even though much advancements have been achieved with regards to the recognition of handwritten characters,researchers still face difficulties with the handwritten character recognition problem,especially with the adv...Even though much advancements have been achieved with regards to the recognition of handwritten characters,researchers still face difficulties with the handwritten character recognition problem,especially with the advent of new datasets like the Extended Modified National Institute of Standards and Technology dataset(EMNIST).The EMNIST dataset represents a challenge for both machine-learning and deep-learning techniques due to inter-class similarity and intra-class variability.Inter-class similarity exists because of the similarity between the shapes of certain characters in the dataset.The presence of intra-class variability is mainly due to different shapes written by different writers for the same character.In this research,we have optimized a deep residual network to achieve higher accuracy vs.the published state-of-the-art results.This approach is mainly based on the prebuilt deep residual network model ResNet18,whose architecture has been enhanced by using the optimal number of residual blocks and the optimal size of the receptive field of the first convolutional filter,the replacement of the first max-pooling filter by an average pooling filter,and the addition of a drop-out layer before the fully connected layer.A distinctive modification has been introduced by replacing the final addition layer with a depth concatenation layer,which resulted in a novel deep architecture having higher accuracy vs.the pure residual architecture.Moreover,the dataset images’sizes have been adjusted to optimize their visibility in the network.Finally,by tuning the training hyperparameters and using rotation and shear augmentations,the proposed model outperformed the state-of-the-art models by achieving average accuracies of 95.91%and 90.90%for the Letters and Balanced dataset sections,respectively.Furthermore,the average accuracies were improved to 95.9%and 91.06%for the Letters and Balanced sections,respectively,by using a group of 5 instances of the trained models and averaging the output class probabilities.展开更多
Few-shot semantic segmentation aims at training a model that can segment novel classes in a query image with only a few densely annotated support exemplars.It remains a challenge because of large intra-class variation...Few-shot semantic segmentation aims at training a model that can segment novel classes in a query image with only a few densely annotated support exemplars.It remains a challenge because of large intra-class variations between the support and query images.Existing approaches utilize 4D convolutions to mine semantic correspondence between the support and query images.However,they still suffer from heavy computation,sparse correspondence,and large memory.We propose axial assembled correspondence network(AACNet)to alleviate these issues.The key point of AACNet is the proposed axial assembled 4D kernel,which constructs the basic block for semantic correspondence encoder(SCE).Furthermore,we propose the deblurring equations to provide more robust correspondence for the aforementioned SCE and design a novel fusion module to mix correspondences in a learnable manner.Experiments on PASCAL-5~i reveal that our AACNet achieves a mean intersection-over-union score of 65.9%for 1-shot segmentation and 70.6%for 5-shot segmentation,surpassing the state-of-the-art method by 5.8%and 5.0%respectively.展开更多
文摘This paper proposes a cascade deep convolutional neural network to address the loosening detection problem of bolts on axlebox covers.Firstly,an SSD network based on ResNet50 and CBAM module by improving bolt image features is proposed for locating bolts on axlebox covers.And then,theA2-PFN is proposed according to the slender features of the marker lines for extracting more accurate marker lines regions of the bolts.Finally,a rectangular approximationmethod is proposed to regularize themarker line regions asaway tocalculate the angle of themarker line and plot all the angle values into an angle table,according to which the criteria of the angle table can determine whether the bolt with the marker line is in danger of loosening.Meanwhile,our improved algorithm is compared with the pre-improved algorithmin the object localization stage.The results show that our proposed method has a significant improvement in both detection accuracy and detection speed,where ourmAP(IoU=0.75)reaches 0.77 and fps reaches 16.6.And in the saliency detection stage,after qualitative comparison and quantitative comparison,our method significantly outperforms other state-of-the-art methods,where our MAE reaches 0.092,F-measure reaches 0.948 and AUC reaches 0.943.Ultimately,according to the angle table,out of 676 bolt samples,a total of 60 bolts are loose,69 bolts are at risk of loosening,and 547 bolts are tightened.
文摘Enabling high mobility applications in millimeter wave(mmWave)based systems opens up a slew of new possibilities,including vehicle communi-cations in addition to wireless virtual/augmented reality.The narrow beam usage in addition to the millimeter waves sensitivity might block the coverage along with the reliability of the mobile links.In this research work,the improvement in the quality of experience faced by the user for multimedia-related applications over the millimeter-wave band is investigated.The high attenuation loss in high frequencies is compensated with a massive array structure named Multiple Input and Multiple Output(MIMO)which is utilized in a hyperdense environment called heterogeneous networks(HetNet).The optimization problem which arises while maximizing the Mean Opinion Score(MOS)is analyzed along with the QoE(Quality of Experience)metric by considering the Base Station(BS)powers in addition to the needed Quality of Service(QoS).Most of the approaches related to wireless network communication are not suitable for the millimeter-wave band because of its problems due to high complexity and its dynamic nature.Hence a deep reinforcement learning framework is developed for tackling the same opti-mization problem.In this work,a Fuzzy-based Deep Convolutional Neural Net-work(FDCNN)is proposed in addition to a Deep Reinforcing Learning Framework(DRLF)for extracting the features of highly correlated data.The investigational results prove that the proposed method yields the highest satisfac-tion to the user by increasing the number of antennas in addition with the small-scale antennas at the base stations.The proposed work outperforms in terms of MOS with multiple antennas.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(NRF-2018R1A2B6007333).
文摘Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However,previous methods have several challenges in costly,time-consuming,and unsafety.To address these drawbacks,this paper proposed a digital vision based concrete compressive strength evaluating model using deep convolutional neural network(DCNN).The proposed model presented an alternative approach to evaluating the concrete strength and contributed to improving efficiency and accuracy.The model was developed with 4,000 digital images and 61,996 images extracted from video recordings collected from concrete samples.The experimental results indicated a root mean square error(RMSE)value of 3.56(MPa),demonstrating a strong feasibility that the proposed model can be utilized to predict the concrete strength with digital images of their surfaces and advantages to overcome the previous limitations.This experiment contributed to provide the basis that could be extended to future research with image analysis technique and artificial neural network in the diagnosis of concrete building structures.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(NRF-2018R1A2B6007333)This study was supported by 2018 Research Grant from Kangwon National University.
文摘In this study,we examined the efficacy of a deep convolutional neural network(DCNN)in recognizing concrete surface images and predicting the compressive strength of concrete.A digital single-lens reflex(DSLR)camera and microscope were simultaneously used to obtain concrete surface images used as the input data for the DCNN.Thereafter,training,validation,and testing of the DCNNs were performed based on the DSLR camera and microscope image data.Results of the analysis indicated that the DCNN employing DSLR image data achieved a relatively higher accuracy.The accuracy of the DSLR-derived image data was attributed to the relatively wider range of the DSLR camera,which was beneficial for extracting a larger number of features.Moreover,the DSLR camera procured more realistic images than the microscope.Thus,when the compressive strength of concrete was evaluated using the DCNN employing a DSLR camera,time and cost were reduced,whereas the usefulness increased.Furthermore,an indirect comparison of the accuracy of the DCNN with that of existing non-destructive methods for evaluating the strength of concrete proved the reliability of DCNN-derived concrete strength predictions.In addition,it was determined that the DCNN used for concrete strength evaluations in this study can be further expanded to detect and evaluate various deteriorative factors that affect the durability of structures,such as salt damage,carbonation,sulfation,corrosion,and freezing-thawing.
文摘The novel coronavirus 2019(COVID-19)rapidly spreading around the world and turns into a pandemic situation,consequently,detecting the coronavirus(COVID-19)affected patients are now the most critical task for medical specialists.The deficiency of medical testing kits leading to huge complexity in detecting COVID-19 patients worldwide,resulting in the number of infected cases is expanding.Therefore,a significant study is necessary about detecting COVID-19 patients using an automated diagnosis method,which hinders the spreading of coronavirus.In this paper,the study suggests a Deep Convolutional Neural Network-based multi-classification framework(COV-MCNet)using eight different pre-trained architectures such as VGG16,VGG19,ResNet50V2,DenseNet201,InceptionV3,MobileNet,InceptionResNetV2,Xception which are trained and tested on the X-ray images of COVID-19,Normal,Viral Pneumonia,and Bacterial Pneumonia.The results from 4-class(Normal vs.COVID-19 vs.Viral Pneumonia vs.Bacterial Pneumonia)demonstrated that the pre-trained model DenseNet201 provides the highest classification performance(accuracy:92.54%,precision:93.05%,recall:92.81%,F1-score:92.83%,specificity:97.47%).Notably,the DenseNet201(4-class classification)pre-trained model in the proposed COV-MCNet framework showed higher accuracy compared to the rest seven models.Important to mention that the proposed COV-MCNet model showed comparatively higher classification accuracy based on the small number of pre-processed datasets that specifies the designed system can produce superior results when more data become available.The proposed multi-classification network(COV-MCNet)significantly speeds up the existing radiology based method which will be helpful for the medical community and clinical specialists to early diagnosis the COVID-19 cases during this pandemic.
基金supported by the National Natural Science Foundation of China-China State Railway Group Co.,Ltd.Railway Basic Research Joint Fund (Grant No.U2268217)the Scientific Funding for China Academy of Railway Sciences Corporation Limited (No.2021YJ183).
文摘Graph Convolutional Neural Networks(GCNs)have been widely used in various fields due to their powerful capabilities in processing graph-structured data.However,GCNs encounter significant challenges when applied to scale-free graphs with power-law distributions,resulting in substantial distortions.Moreover,most of the existing GCN models are shallow structures,which restricts their ability to capture dependencies among distant nodes and more refined high-order node features in scale-free graphs with hierarchical structures.To more broadly and precisely apply GCNs to real-world graphs exhibiting scale-free or hierarchical structures and utilize multi-level aggregation of GCNs for capturing high-level information in local representations,we propose the Hyperbolic Deep Graph Convolutional Neural Network(HDGCNN),an end-to-end deep graph representation learning framework that can map scale-free graphs from Euclidean space to hyperbolic space.In HDGCNN,we define the fundamental operations of deep graph convolutional neural networks in hyperbolic space.Additionally,we introduce a hyperbolic feature transformation method based on identity mapping and a dense connection scheme based on a novel non-local message passing framework.In addition,we present a neighborhood aggregation method that combines initial structural featureswith hyperbolic attention coefficients.Through the above methods,HDGCNN effectively leverages both the structural features and node features of graph data,enabling enhanced exploration of non-local structural features and more refined node features in scale-free or hierarchical graphs.Experimental results demonstrate that HDGCNN achieves remarkable performance improvements over state-ofthe-art GCNs in node classification and link prediction tasks,even when utilizing low-dimensional embedding representations.Furthermore,when compared to shallow hyperbolic graph convolutional neural network models,HDGCNN exhibits notable advantages and performance enhancements.
文摘Watermarking is the advanced technology utilized to secure digital data by integrating ownership or copyright protection.Most of the traditional extracting processes in audio watermarking have some restrictions due to low reliability to various attacks.Hence,a deep learning-based audio watermarking system is proposed in this research to overcome the restriction in the traditional methods.The implication of the research relies on enhancing the performance of the watermarking system using the Discrete Wavelet Transform(DWT)and the optimized deep learning technique.The selection of optimal embedding location is the research contribution that is carried out by the deep convolutional neural network(DCNN).The hyperparameter tuning is performed by the so-called search location optimization,which minimizes the errors in the classifier.The experimental result reveals that the proposed digital audio watermarking system provides better robustness and performance in terms of Bit Error Rate(BER),Mean Square Error(MSE),and Signal-to-noise ratio.The BER,MSE,and SNR of the proposed audio watermarking model without the noise are 0.082,0.099,and 45.363 respectively,which is found to be better performance than the existing watermarking models.
文摘The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software with defects negatively impacts operational costs and finally affects customer satisfaction. Numerous approaches exist to predict software defects. However, the timely and accurate software bugs are the major challenging issues. To improve the timely and accurate software defect prediction, a novel technique called Nonparametric Statistical feature scaled QuAdratic regressive convolution Deep nEural Network (SQADEN) is introduced. The proposed SQADEN technique mainly includes two major processes namely metric or feature selection and classification. First, the SQADEN uses the nonparametric statistical Torgerson–Gower scaling technique for identifying the relevant software metrics by measuring the similarity using the dice coefficient. The feature selection process is used to minimize the time complexity of software fault prediction. With the selected metrics, software fault perdition with the help of the Quadratic Censored regressive convolution deep neural network-based classification. The deep learning classifier analyzes the training and testing samples using the contingency correlation coefficient. The softstep activation function is used to provide the final fault prediction results. To minimize the error, the Nelder–Mead method is applied to solve non-linear least-squares problems. Finally, accurate classification results with a minimum error are obtained at the output layer. Experimental evaluation is carried out with different quantitative metrics such as accuracy, precision, recall, F-measure, and time complexity. The analyzed results demonstrate the superior performance of our proposed SQADEN technique with maximum accuracy, sensitivity and specificity by 3%, 3%, 2% and 3% and minimum time and space by 13% and 15% when compared with the two state-of-the-art methods.
基金the Fundamental Research Funds for the Central Universities(2572018BC07,2572017PZ14)the Heilongjiang postdoctoral project fund project(LBH-Z18003)+2 种基金Biodiversity Survey,Monitoring and Assessment Project of Ministry of Ecology and Environment,China(2019HB2096001006)the National Natural Science Foundation of China(NSFC 31872241,31572285)the Individual Identification Technological Research on Camera-trapping images of Amur tigers(NFGA 2017).
文摘The automatic individual identification of Amur tigers(Panthera tigris altaica)is important for population monitoring and making effective conservation strategies.Most existing research primarily relies on manual identifi-cation,which does not scale well to large datasets.In this paper,the deep convolution neural networks algorithm is constructed to implement the automatic individual identification for large numbers of Amur tiger images.The experimental data were obtained from 40 Amur tigers in Tieling Guaipo Tiger Park,China.The number of images collected from each tiger was approximately 200,and a total of 8277 images were obtained.The experiments were carried out on both the left and right side of body.Our results suggested that the recognition accuracy rate of left and right sides are 90.48%and 93.5%,respectively.The accuracy of our network has achieved the similar level compared to other state of the art networks like LeNet,ResNet34,and ZF_Net.The running time is much shorter than that of other networks.Consequently,this study can provide a new approach on automatic individual identification technology in the case of the Amur tiger.
文摘Skin lesions are in a category of disease that is both common in humans and a major cause of death.The classification accuracy of skin lesions is a crucial determinant of the success rate of curing lethal diseases.Deep Convolutional Neural Networks(CNNs)are now the most prevalent computer algorithms for the purpose of disease classification.As with all algorithms,CNNs are sensitive to noise from imaging devices,which often contaminates the quality of the images that are fed into them.In this paper,a deep CNN(Inception-v3)is used to study the effect of image noise on the classification of skin lesions.Gaussian noise,impulse noise,and noise made up of a compound of the two are added to an image dataset,namely the Dermofit Image Library from the University of Edinburgh.Evaluations,based on t-distributed Stochastic Neighbor Embedding(t-SNE)visualization,Receiver Operating Characteristic(ROC)analysis,and saliency maps,demonstrate the reliability of the Inception-v3 deep CNN in classifying noisy skin lesion images.
基金supported by the National Natural Science Foundation of China (61320106006, 61532006, 61502042)
文摘Existing learning-based super-resolution (SR) reconstruction algorithms are mainly designed for single image, which ignore the spatio-temporal relationship between video frames. Aiming at applying the advantages of learning-based algorithms to video SR field, a novel video SR reconstruction algorithm based on deep convolutional neural network (CNN) and spatio-temporal similarity (STCNN-SR) was proposed in this paper. It is a deep learning method for video SR reconstruction, which considers not onlv the mapping relationship among associated low-resolution (LR) and high-resolution (HR) image blocks, but also the spatio-temporal non-local complementary and redundant information between adjacent low-resolution video frames. The reconstruction speed can be improved obviously with the pre-trained end-to-end reconstructed coefficients. Moreover, the performance of video SR will be further improved by the optimization process with spatio-temporal similarity. Experimental results demonstrated that the proposed algorithm achieves a competitive SR quality on both subjective and objective evaluations, when compared to other state-of-the-art algorithms.
基金supported by the UK Engineering and Physical Science Research Council(EP/K000128/1)and the China Scholarship Council.
文摘Deformable microcapsules are widely used in industries and also serve as a mechanical model of living biological cells.In this study,we develop a novel method,by integrating a deep convolutional neural network(DCNN)with high-fidelity mechanistic capsule modelling,to identify the membrane constitutive law and estimate associated parameters of a microcapsule from its steady deformed profile in a capillary tube.Compared with conventional inverse methods,the present approach is more accurate and can increase the prediction throughput rate by a few orders of magnitude.It can process capsules with large deformation in inertial flows.Furthermore,the method can predict the capsule membrane shear elasticity,area dilatation modulus and initial inflation from a single steady capsule profile.We explore the mechanism that the DCNN makes decisions by considering its feature maps,and discuss their potential implication on the development of inverse methods.The present method provides a promising tool which may enable high-throughput mechanical characterisation of microcapsules and biological cells in microfluidic flows.
基金supported by the Natural Science Foundation of Hebei Provence[grant numbers:F2015201033,F2017201069]the foundation of H3C[grant number:2017A20004]。
文摘Since of the scale and the various shapes of down in the image,it is difficult for traditional image recognition method to correctly recognize the type of down image and get the required recognition accuracy,even for the Traditional Convolutional Neural Network(TCNN).To deal with the above problems,a Deep Convolutional Neural Network(DCNN)for down image classification is constructed,and a new weight initialization method is proposed.Firstly,the salient regions of a down image were cut from the image using the visual saliency model.Then,these salient regions of the image were used to train a sparse autoencoder and get a collection of convolutional filters,which accord with the statistical characteristics of dataset.At last,a DCNN with Inception module and its variants was constructed.To improve the recognition accuracy,the depth of the network is deepened.The experiment results indicate that the constructed DCNN increases the recognition accuracy by 2.7% compared to TCNN,when recognizing the down in the images.The convergence rate of the proposed DCNN with the new weight initialization method is improved by 25.5% compared to TCNN.
文摘In recent years,computer visionfinds wide applications in maritime surveillance with its sophisticated algorithms and advanced architecture.Auto-matic ship detection with computer vision techniques provide an efficient means to monitor as well as track ships in water bodies.Waterways being an important medium of transport require continuous monitoring for protection of national security.The remote sensing satellite images of ships in harbours and water bodies are the image data that aid the neural network models to localize ships and to facilitate early identification of possible threats at sea.This paper proposes a deep learning based model capable enough to classify between ships and no-ships as well as to localize ships in the original images using bounding box tech-nique.Furthermore,classified ships are again segmented with deep learning based auto-encoder model.The proposed model,in terms of classification,provides suc-cessful results generating 99.5%and 99.2%validation and training accuracy respectively.The auto-encoder model also produces 85.1%and 84.2%validation and training accuracies.Moreover the IoU metric of the segmented images is found to be of 0.77 value.The experimental results reveal that the model is accu-rate and can be implemented for automatic ship detection in water bodies consid-ering remote sensing satellite images as input to the computer vision system.
文摘Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.
文摘Early diagnosis and detection are important tasks in controlling the spread of COVID-19.A number of Deep Learning techniques has been established by researchers to detect the presence of COVID-19 using CT scan images and X-rays.However,these methods suffer from biased results and inaccurate detection of the disease.So,the current research article developed Oppositional-based Chimp Optimization Algorithm and Deep Dense Convolutional Neural Network(OCOA-DDCNN)for COVID-19 prediction using CT images in IoT environment.The proposed methodology works on the basis of two stages such as pre-processing and prediction.Initially,CT scan images generated from prospective COVID-19 are collected from open-source system using IoT devices.The collected images are then preprocessed using Gaussian filter.Gaussian filter can be utilized in the removal of unwanted noise from the collected CT scan images.Afterwards,the preprocessed images are sent to prediction phase.In this phase,Deep Dense Convolutional Neural Network(DDCNN)is applied upon the pre-processed images.The proposed classifier is optimally designed with the consideration of Oppositional-basedChimp Optimization Algorithm(OCOA).This algorithm is utilized in the selection of optimal parameters for the proposed classifier.Finally,the proposed technique is used in the prediction of COVID-19 and classify the results as either COVID-19 or non-COVID-19.The projected method was implemented in MATLAB and the performances were evaluated through statistical measurements.The proposed method was contrasted with conventional techniques such as Convolutional Neural Network-Firefly Algorithm(CNN-FA),Emperor Penguin Optimization(CNN-EPO)respectively.The results established the supremacy of the proposed model.
文摘The most widely farmed fruit in the world is mango.Both the production and quality of the mangoes are hampered by many diseases.These diseases need to be effectively controlled and mitigated.Therefore,a quick and accurate diagnosis of the disorders is essential.Deep convolutional neural networks,renowned for their independence in feature extraction,have established their value in numerous detection and classification tasks.However,it requires large training datasets and several parameters that need careful adjustment.The proposed Modified Dense Convolutional Network(MDCN)provides a successful classification scheme for plant diseases affecting mango leaves.This model employs the strength of pre-trained networks and modifies them for the particular context of mango leaf diseases by incorporating transfer learning techniques.The data loader also builds mini-batches for training the models to reduce training time.Finally,optimization approaches help increase the overall model’s efficiency and lower computing costs.MDCN employed on the MangoLeafBD Dataset consists of a total of 4,000 images.Following the experimental results,the proposed system is compared with existing techniques and it is clear that the proposed algorithm surpasses the existing algorithms by achieving high performance and overall throughput.
基金This work was supported by Special Funds for the Construction of an Innovative Province of Hunan(GrantNo.2020GK2028)lNatural Science Foundation of Hunan Province(Grant No.2022JJ30002)lScientific Research Project of Hunan Provincial EducationDepartment(GrantNo.21B0833)lScientific Research Key Project of Hunan Education Department(Grant No.21A0592)lScientific Research Project of Hunan Provincial Education Department(Grant No.22A0663).
文摘Deep Convolutional Neural Networks(CNNs)have achieved high accuracy in image classification tasks,however,most existing models are trained on high-quality images that are not subject to image degradation.In practice,images are often affected by various types of degradation which can significantly impact the performance of CNNs.In this work,we investigate the influence of image degradation on three typical image classification CNNs and propose a Degradation Type Adaptive Image Classification Model(DTA-ICM)to improve the existing CNNs’classification accuracy on degraded images.The proposed DTA-ICM comprises two key components:a Degradation Type Predictor(DTP)and a Degradation Type Specified Image Classifier(DTS-IC)set,which is trained on existing CNNs for specified types of degradation.The DTP predicts the degradation type of a test image,and the corresponding DTS-IC is then selected to classify the image.We evaluate the performance of both the proposed DTP and the DTA-ICMon the Caltech 101 database.The experimental results demonstrate that the proposed DTP achieves an average accuracy of 99.70%.Moreover,the proposed DTA-ICM,based on AlexNet,VGG19,and ResNet152,exhibits an average accuracy improvement of 20.63%,18.22%,and 12.9%,respectively,compared with the original CNNs in classifying degraded images.It suggests that the proposed DTA-ICM can effectively improve the classification performance of existing CNNs on degraded images,which has important practical implications.
文摘Even though much advancements have been achieved with regards to the recognition of handwritten characters,researchers still face difficulties with the handwritten character recognition problem,especially with the advent of new datasets like the Extended Modified National Institute of Standards and Technology dataset(EMNIST).The EMNIST dataset represents a challenge for both machine-learning and deep-learning techniques due to inter-class similarity and intra-class variability.Inter-class similarity exists because of the similarity between the shapes of certain characters in the dataset.The presence of intra-class variability is mainly due to different shapes written by different writers for the same character.In this research,we have optimized a deep residual network to achieve higher accuracy vs.the published state-of-the-art results.This approach is mainly based on the prebuilt deep residual network model ResNet18,whose architecture has been enhanced by using the optimal number of residual blocks and the optimal size of the receptive field of the first convolutional filter,the replacement of the first max-pooling filter by an average pooling filter,and the addition of a drop-out layer before the fully connected layer.A distinctive modification has been introduced by replacing the final addition layer with a depth concatenation layer,which resulted in a novel deep architecture having higher accuracy vs.the pure residual architecture.Moreover,the dataset images’sizes have been adjusted to optimize their visibility in the network.Finally,by tuning the training hyperparameters and using rotation and shear augmentations,the proposed model outperformed the state-of-the-art models by achieving average accuracies of 95.91%and 90.90%for the Letters and Balanced dataset sections,respectively.Furthermore,the average accuracies were improved to 95.9%and 91.06%for the Letters and Balanced sections,respectively,by using a group of 5 instances of the trained models and averaging the output class probabilities.
基金supported in part by the Key Research and Development Program of Guangdong Province(2021B0101200001)the Guangdong Basic and Applied Basic Research Foundation(2020B1515120071)。
文摘Few-shot semantic segmentation aims at training a model that can segment novel classes in a query image with only a few densely annotated support exemplars.It remains a challenge because of large intra-class variations between the support and query images.Existing approaches utilize 4D convolutions to mine semantic correspondence between the support and query images.However,they still suffer from heavy computation,sparse correspondence,and large memory.We propose axial assembled correspondence network(AACNet)to alleviate these issues.The key point of AACNet is the proposed axial assembled 4D kernel,which constructs the basic block for semantic correspondence encoder(SCE).Furthermore,we propose the deblurring equations to provide more robust correspondence for the aforementioned SCE and design a novel fusion module to mix correspondences in a learnable manner.Experiments on PASCAL-5~i reveal that our AACNet achieves a mean intersection-over-union score of 65.9%for 1-shot segmentation and 70.6%for 5-shot segmentation,surpassing the state-of-the-art method by 5.8%and 5.0%respectively.