Bridge Crack Segmentation Method Based on Parallel Attention Mechanism and Multi-Scale Features Fusion

Regular inspection of bridge cracks is crucial to bridge maintenance and repair.The traditional manual crack detection methods are timeconsuming,dangerous and subjective.At the same time,for the existing mainstream vision-based automatic crack detection algorithms,it is challenging to detect fine cracks and balance the detection accuracy and speed.Therefore,this paper proposes a new bridge crack segmentationmethod based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+network framework.First,the improved lightweight MobileNetv2 network and dilated separable convolution are integrated into the original DeeplabV3+network to improve the original backbone network Xception and atrous spatial pyramid pooling(ASPP)module,respectively,dramatically reducing the number of parameters in the network and accelerates the training and prediction speed of the model.Moreover,we introduce the parallel attention mechanism into the encoding and decoding stages.The attention to the crack regions can be enhanced from the aspects of both channel and spatial parts and significantly suppress the interference of various noises.Finally,we further improve the detection performance of the model for fine cracks by introducing a multi-scale features fusion module.Our research results are validated on the self-made dataset.The experiments show that our method is more accurate than other methods.Its intersection of union(IoU)and F1-score(F1)are increased to 77.96%and 87.57%,respectively.In addition,the number of parameters is only 4.10M,which is much smaller than the original network;also,the frames per second(FPS)is increased to 15 frames/s.The results prove that the proposed method fits well the requirements of rapid and accurate detection of bridge cracks and is superior to other methods.

Scheme Based on Multi-Level Patch Attention and Lesion Localization for Diabetic Retinopathy Grading

Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.

Bilateral U-Net semantic segmentation with spatial attention mechanism

Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.

AF-Net:A Medical Image Segmentation Network Based on Attention Mechanism and Feature Fusion

Medical image segmentation is an important application field of computer vision in medical image processing.Due to the close location and high similarity of different organs in medical images,the current segmentation algorithms have problems with mis-segmentation and poor edge segmentation.To address these challenges,we propose a medical image segmentation network(AF-Net)based on attention mechanism and feature fusion,which can effectively capture global information while focusing the network on the object area.In this approach,we add dual attention blocks(DA-block)to the backbone network,which comprises parallel channels and spatial attention branches,to adaptively calibrate and weigh features.Secondly,the multi-scale feature fusion block(MFF-block)is proposed to obtain feature maps of different receptive domains and get multi-scale information with less computational consumption.Finally,to restore the locations and shapes of organs,we adopt the global feature fusion blocks(GFF-block)to fuse high-level and low-level information,which can obtain accurate pixel positioning.We evaluate our method on multiple datasets(the aorta and lungs dataset),and the experimental results achieve 94.0%in mIoU and 96.3%in DICE,showing that our approach performs better than U-Net and other state-of-art methods.

基于Attention-BiTCN的网络入侵检测方法

为解决网络入侵检测领域多分类准确率不高的问题,文章根据网络流量数据具有时序特征的特点,提出一种基于注意力机制和双向时间卷积神经网络(BiDirectional Temporal Convolutional Network,BiTCN)的网络入侵检测模型。首先,该模型对数据集进行独热编码和归一化处置等预处理,解决网络流量数据离散性强和标度不统一的问题;其次,将预处理好的数据经双向滑窗法生成双向序列,并同步输入Attention-Bi TCN模型中;然后,提取双向时序特征并通过加性方式融合,得到时序信息被增强后的融合特征;最后,使用Softmax函数对融合特征进行多种攻击行为检测识别。文章所提模型在NSL-KDD和UNSW-NB15数据集上进行实验验证,多分类准确率分别达到99.70%和84.07%,优于传统网络入侵检测算法,且比其他深度学习模型在检测性能上有显著提升。

Multimodal Sentiment Analysis Using BiGRU and Attention-Based Hybrid Fusion Strategy

Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimodal sentiment analysis is how to design an efficient multimodal feature fusion strategy.Unfortunately,existing work always considers feature-level fusion or decision-level fusion,and few research works focus on hybrid fusion strategies that contain feature-level fusion and decision-level fusion.To improve the performance of multimodal sentiment analysis,we present a novel multimodal sentiment analysis model using BiGRU and attention-based hybrid fusion strategy(BAHFS).Firstly,we apply BiGRU to learn the unimodal features of text,audio and video.Then we fuse the unimodal features into bimodal features using the bimodal attention fusion module.Next,BAHFS feeds the unimodal features and bimodal features into the trimodal attention fusion module and the trimodal concatenation fusion module simultaneously to get two sets of trimodal features.Finally,BAHFS makes a classification with the two sets of trimodal features respectively and gets the final analysis results with decision-level fusion.Based on the CMU-MOSI and CMU-MOSEI datasets,extensive experiments have been carried out to verify BAHFS’s superiority.

Multiscale feature learning and attention mechanism for infrared and visible image fusion

Current fusion methods for infrared and visible images tend to extract features at a single scale,which results in insufficient detail and incomplete feature preservation.To address these issues,we propose an infrared and visible image fusion network based on a multiscale feature learning and attention mechanism(MsAFusion).A multiscale dilation convolution framework is employed to capture image features across various scales and broaden the perceptual scope.Furthermore,an attention network is introduced to enhance the focus on salient targets in infrared images and detailed textures in visible images.To compensate for information loss during convolution,jump connections are utilized during the image reconstruction phase.The fusion process utilizes a combined loss function consisting of pixel loss and gradient loss for unsupervised fusion of infrared and visible images.Extensive experiments on the dataset of electricity facilities demonstrate that our proposed method outperforms nine state-of-theart methods in terms of visual perception and four objective evaluation metrics.

Fusion network for small target detection based on YOLO and attention mechanism

Target detection is an important task in computer vision research, and such an anomaly detection and the topic of small target detection task is more concerned. However, there are still some problems in this kind of researches, such as small target detection in complex environments is susceptible to background interference and poor detection results. To solve these issues, this study proposes a method which introduces the attention mechanism into the you only look once(YOLO) network. In addition, the amateur-produced mask dataset was created and experiments were conducted. The results showed that the detection effect of the proposed mothed is much better.

基于改进Centerfusion的自动驾驶3D目标检测模型

针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富的3D目标检测信息,引入了改进的注意力机制,用于增强视锥网格中的雷达点云和视觉信息融合;使用改进的损失函数优化边框预测的准确度。在Nuscenes数据集上进行模型验证和对比,实验结果表明,相较于传统的Centerfusion模型,提出的模型平均检测精度均值(mean Average Precision,mAP)提高了1.3%,Nuscenes检测分数(Nuscenes Detection Scores,NDS)提高了1.2%。

Transformer architecture based on mutual attention for image-anomaly detection

Image-anomaly detection, which is widely used in industrial fields. Previous studies that attempted to address this problem often trained convolutional neural network-based models(e.g., autoencoders and generative adversarial networks) to reconstruct covered parts of input images and calculate the difference between the input and reconstructed images. However, convolutional operations are effective at extracting local features, making it difficult to identify larger image anomalies. Method To this end, we propose a transformer architecture based on mutual attention for image-anomaly separation. This architecture can capture long-term dependencies and fuse local and global features to facilitate better image-anomaly detection. Result Our method was extensively evaluated on several benchmarks, and experimental results showed that it improved the detection capability by 3.1% and localization capability by 1.0% compared with state-of-the-art reconstruction-based methods.

Multi-Feature Fusion-Guided Multiscale Bidirectional Attention Networks for Logistics Pallet Segmentation

In the smart logistics industry,unmanned forklifts that intelligently identify logistics pallets can improve work efficiency in warehousing and transportation and are better than traditional manual forklifts driven by humans.Therefore,they play a critical role in smart warehousing,and semantics segmentation is an effective method to realize the intelligent identification of logistics pallets.However,most current recognition algorithms are ineffective due to the diverse types of pallets,their complex shapes,frequent blockades in production environments,and changing lighting conditions.This paper proposes a novel multi-feature fusion-guided multiscale bidirectional attention(MFMBA)neural network for logistics pallet segmentation.To better predict the foreground category(the pallet)and the background category(the cargo)of a pallet image,our approach extracts three types of features(grayscale,texture,and Hue,Saturation,Value features)and fuses them.The multiscale architecture deals with the problem that the size and shape of the pallet may appear different in the image in the actual,complex environment,which usually makes feature extraction difficult.Our study proposes a multiscale architecture that can extract additional semantic features.Also,since a traditional attention mechanism only assigns attention rights from a single direction,we designed a bidirectional attention mechanism that assigns cross-attention weights to each feature from two directions,horizontally and vertically,significantly improving segmentation.Finally,comparative experimental results show that the precision of the proposed algorithm is 0.53%–8.77%better than that of other methods we compared.

CAW-YOLO:Cross-Layer Fusion and Weighted Receptive Field-Based YOLO for Small Object Detection in Remote Sensing

In recent years,there has been extensive research on object detection methods applied to optical remote sensing images utilizing convolutional neural networks.Despite these efforts,the detection of small objects in remote sensing remains a formidable challenge.The deep network structure will bring about the loss of object features,resulting in the loss of object features and the near elimination of some subtle features associated with small objects in deep layers.Additionally,the features of small objects are susceptible to interference from background features contained within the image,leading to a decline in detection accuracy.Moreover,the sensitivity of small objects to the bounding box perturbation further increases the detection difficulty.In this paper,we introduce a novel approach,Cross-Layer Fusion and Weighted Receptive Field-based YOLO(CAW-YOLO),specifically designed for small object detection in remote sensing.To address feature loss in deep layers,we have devised a cross-layer attention fusion module.Background noise is effectively filtered through the incorporation of Bi-Level Routing Attention(BRA).To enhance the model’s capacity to perceive multi-scale objects,particularly small-scale objects,we introduce a weightedmulti-receptive field atrous spatial pyramid poolingmodule.Furthermore,wemitigate the sensitivity arising from bounding box perturbation by incorporating the joint Normalized Wasserstein Distance(NWD)and Efficient Intersection over Union(EIoU)losses.The efficacy of the proposedmodel in detecting small objects in remote sensing has been validated through experiments conducted on three publicly available datasets.The experimental results unequivocally demonstrate the model’s pronounced advantages in small object detection for remote sensing,surpassing the performance of current mainstream models.

基于MCFFN-Attention的高光谱图像分类

针对高光谱图像高维度的特性和样本数量少的局限性,提出了一个多尺度跨层特征融合注意力机制(MCFFN-Attention)的方法。对高光谱图像进行PCA降维,然后以3D CNN为基础,将中心像素和其相邻像素作为整体输入到网络中,对不同卷积层得到的特征进行融合。同时对融合的低层特征进行空间注意力机制处理,对融合的高层特征进行通道注意力机制处理,分配给它们不同的权重来优化特征图。在印第安松树和帕维亚大学数据集上进行实验,结果表明此方法相对于CNN、3D CNN和M3D CNN方法,分类精度得到了提升。

Attention-Based CNN Fusion Model for Emotion Recognition During Walking Using Discrete Wavelet Transform on EEG and Inertial Signals

Walking as a unique biometric tool conveys important information for emotion recognition.Individuals in different emotional states exhibit distinct walking patterns.For this purpose,this paper proposes a novel approach to recognizing emotion during walking using electroencephalogram(EEG)and inertial signals.Accurate recognition of emotion is achieved by training in an end-to-end deep learning fashion and taking into account multi-modal fusion.Subjects wear virtual reality head-mounted display(VR-HMD)equipment to immerse in strong emotions during walking.VR environment shows excellent imitation and experience ability,which plays an important role in awakening and changing emotions.In addition,the multi-modal signals acquired from EEG and inertial sensors are separately represented as virtual emotion images by discrete wavelet transform(DWT).These serve as input to the attention-based convolutional neural network(CNN)fusion model.The designed network structure is simple and lightweight while integrating the channel attention mechanism to extract and enhance features.To effectively improve the performance of the recognition system,the proposed decision fusion algorithm combines Critic method and majority voting strategy to determine the weight values that affect the final decision results.An investigation is made on the effect of diverse mother wavelet types and wavelet decomposition levels on model performance which indicates that the 2.2-order reverse biorthogonal(rbio2.2)wavelet with two-level decomposition has the best recognition performance.Comparative experiment results show that the proposed method outperforms other existing state-of-the-art works with an accuracy of 98.73%.

基于LSTM-Attention与CNN混合模型的文本分类方法

针对传统长短时记忆网络(LongShort-TermMemory,LSTM)和卷积神经网络(ConvolutionNeuralNetwork,CNN)在提取特征时无法体现每个词语在文本中重要程度的问题,提出一种基于LSTM-Attention与CNN混合模型的文本分类方法。使用CNN提取文本局部信息,进而整合出全文语义;用LSTM提取文本上下文特征,在LSTM之后加入注意力机制(Attention)提取输出信息的注意力分值;将LSTM-Attention的输出与CNN的输出进行融合,实现了有效提取文本特征的基础上将注意力集中在重要的词语上。在三个公开数据集上的实验结果表明,提出的模型相较于LSTM、CNN及其改进模型效果更好,可以有效提高文本分类的效果。

基于GLSTM和Attention的中文事件要素提取

事件信息抽取是信息抽取任务中的一种,旨在识别并提出一个事件的触发词和元素。由于容易受到数据稀疏的影响,事件要素的抽取是中文事件抽取任务中的一个难点,研究的重点在于特征工程的构建。中文语法相较英文要复杂许多,所以捕获英文文本特征的方法在中文任务中效果并不明显,而目前常用的神经网络模型仅考虑了上下文信息,不能兼顾词法和句法特征。因此针对中文的词法和句法特点,构建一种结合分组长短期记忆网络(grouped long-short term memory,GLSTM)和Attention的中文事件要素抽取方法 AGCEE(attention and GLSTM based Chinese event extraction),通过Attention机制融合词特征和句子特征,采用GLSTM捕获句子的上下文信息,并通过条件随机场(conditional random fields,CRF)进行事件信息抽取,最后在公开数据集上进行实验以验证模型的有效性。

MFF-Net: Multimodal Feature Fusion Network for 3D Object Detection

In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection will be affected by problems such as illumination changes,object occlusion,and object detection distance.To this purpose,we face these challenges by proposing a multimodal feature fusion network for 3D object detection(MFF-Net).In this research,this paper first uses the spatial transformation projection algorithm to map the image features into the feature space,so that the image features are in the same spatial dimension when fused with the point cloud features.Then,feature channel weighting is performed using an adaptive expression augmentation fusion network to enhance important network features,suppress useless features,and increase the directionality of the network to features.Finally,this paper increases the probability of false detection and missed detection in the non-maximum suppression algo-rithm by increasing the one-dimensional threshold.So far,this paper has constructed a complete 3D target detection network based on multimodal feature fusion.The experimental results show that the proposed achieves an average accuracy of 82.60%on the Karlsruhe Institute of Technology and Toyota Technological Institute(KITTI)dataset,outperforming previous state-of-the-art multimodal fusion networks.In Easy,Moderate,and hard evaluation indicators,the accuracy rate of this paper reaches 90.96%,81.46%,and 75.39%.This shows that the MFF-Net network has good performance in 3D object detection.

降质靶标检测算法

装甲车辆动态性能考核中的立靶成像测试环节,靶标检测的准确性与武器装备鉴定及定型的精度息息相关。针对靶标图像对比度低、可辨识度低等降质问题,提出一种基于改进YOLOv5的降质靶标检测算法:使用多分支分组卷积结构配合深度、逐点卷积搭建主干特征提取网络,降低网络参数计算量,提高网络的检测速度;引入表征注意力机制,增强靶标的表征能力;在网络输出层,引入3分支空间特征融合,利用低层特征图的细粒度特征信息与高层特征图丰富的语义信息组合,保留降质靶标图像的细节、边缘语义信息;实验结果表明:在靶标数据集中,所提算法的检测精度mAP达到90.88%,检测速度达到52.74帧/s,能在降质环境下够高效、精准地完成动态性能考核中立靶成像测试环节中的靶标检测部分。

非结构化数据表征增强的术后风险预测模型

准确的术后风险预测对临床资源的规划、应急方案的准备以及患者术后风险和死亡率的降低具有积极的作用。目前,术后风险预测主要基于患者的基本信息、术前的实验室检查及术中的生命体征等结构化数据,蕴含着丰富语义信息的非结构化术前诊断的价值尚待验证。针对上述问题,该文提出一种非结构化数据表征增强的术后风险预测模型,利用自注意力机制,将结构化数据与术前诊断进行信息加权融合。基于临床数据,该文将所提出的模型与术后风险预测常用的统计机器学习模型以及最新的深度神经网络进行对比,在肺部并发症风险预测、ICU入室风险预测和心血管不良风险预测任务上的F1值平均提升了9.533%,同时预测模型还具有良好的可解释性。

基于注意力与多级特征融合的YOLOv5算法

针对复杂场景下目标检测与识别精度较低的问题,提出了一种基于注意力与多级特征融合的YOLOv5目标检测与识别算法。该算法在传统YOLOv5s模型的主干网络中引入双空间方向的金字塔切分注意力机制,增强对特征空间和通道信息的学习能力,同时在瓶颈网络中采用多级特征融合结构,对不同分支的特征进行融合,增加特征的丰富性,提升应对复杂场景的能力。此外,利用C3Ghost模块和深度可分离卷积分别替换C3模块和普通卷积,降低网络参数量和复杂度。结果表明:与传统的YOLOv5s算法相比,所提算法在VOC2007+2012数据集的均值平均精度高达85%,在智能零售柜商品识别数据集的均值平均精度高达97.2%,表现出较好的性能。