基于Transformer改进的YOLOv5+DeepSORT的车辆跟踪算法

针对传统目标检测跟踪算法检测精度低、全局感知能力差、对遮挡和小目标物体的识别能力差等问题,提出了一种基于轻量化Transformer改进的YOLOv5和DeepSORT算法的车辆跟踪方法。首先,利用EfficientFormerV2模型改进YOLOv5算法模型,增强车辆的目标检测能力;然后,利用移位窗口(Swin)模型的优点改进DeepSORT多目标跟踪算法中的重识别(Re-Identification)模块,提高车辆的跟踪能力和精度;最后,通过数据集KITTI和VeRi开展对比试验和消融实验。结果表明,在复杂工况下,该方法的性能在车辆遮挡和小目标识别方面显著提高,平均准确度达到96.7%,目标跟踪准确度提高了9.547%,编号(ID)切换总次数减少了26.4%。

M^(3)Res-Transformer:新冠肺炎胸部X-ray图像识别模型

新冠肺炎(COVID-19)自爆发以来严重影响人类生命健康,近年来残差神经网络广泛应用于COVID-19识别任务中,辅助医生快速地诊断COVID-19患者,但是COVID-19图像病变区域形状复杂、大小不一,与周围组织的边界模糊,导致网络难以提取有效特征.本文针对上述问题,提出一种M^(3)Res-Transformer的新冠肺炎胸部X-ray图像识别模型,采用Res-Transformer作为模型的主干网络,结合ResNet和ViT,有效地整合局部病变特征和全局特征;设计混合残差注意力模块(mixed residual attention Module,mraM),同时考虑通道和空间位置的相互依赖性,增强网络的特征表达能力;为了增大感受野,提取多尺度特征,通过叠加具有不同扩张率的扩张卷积构造多尺度扩张残差模块(multiscale dilated residual Module,mdrM),根据不同层次特征尺度的差异,使用3个逐渐收缩尺度的mdrM进行多尺度特征提取;提出上下文交叉感知模块(contextual cross-awareness Module,ccaM),使用深层特征中的语义信息来引导浅层特征,然后将浅层特征中的空间信息嵌入深层特征中,采用交叉加权注意力机制高效聚合深层和浅层特征,获得更丰富的上下文信息.为了验证本文所提模型的有效性,在新冠肺炎胸部X-ray图像数据集上进行实验,与先进的CNN分类模型、融合不同注意力机制的ResNet50模型、基于Transformer的分类模型对比以及消融实验.结果表明,本文所提模型的Acc、Pre、Rec、F1-Score与Spe指标分别为96.33%、96.36%、96.33%、96.35%与96.26%,在COVID-19胸部X-ray图像识别任务中有效提升了识别精度,并通过可视化方法对其进行进一步验证,为COVID-19的辅助诊断提供重要的参考价值.

基于改进YOLOv5s的CNN-Swin Transformer森林野生动物图像目标检测算法

【目的】为提高野生动物在复杂森林环境中的检测精度,促进森林野生动物保护技术发展,提出一种基于YOLOv5s网络模型、针对陷阱相机所摄取森林野生动物图像的改进检测算法。【方法】以包含湖南壶瓶山国家级自然保护区几种典型森林野生动物在内的数据集为研究对象,首先,对真实标注框图像进行裁剪、归一化和缩放处理,随机将2~4张裁剪图像拼贴组成新的数据集元素,以丰富和增强数据集图像信息;其次,使用一种基于通道注意力思想的加权通道拼接方法,在通道拼接时引入权重改变通道数量,通过反向传播训练方法不断更新权重以增加重要特征信息的通道层数;接着,引入Swin Transformer模块与CNN网络相结合,为卷积神经网络特征提取加入自注意力机制,融合2种网络特征提取层的优势,提高特征提取的感受野;最后,选择更优的α-DIoU损失函数替代GIoU损失函数,针对边界框重叠面积和中心点距离造成的损失,引入新的几何因素惩罚项。【结果】在相同试验条件和数据集下,相比原YOLOv5s网络模型,改进算法极大提高检测的平均准确率和平均回归率,均值平均精度由74.1%提升至88.4%,获得14.3%的精度提升,同时也超过YOLOv3、YOLOXs、RetinaNet、Faster R-CNN等其他流行目标检测算法。【结论】针对陷阱相机所摄取森林野生动物图像背景与目标对比度低、遮挡重叠严重,致使检测误检率、漏检率高等问题,在检测算法中提出一系列改进措施,为我国森林野生动物的保护和数据获取提供一种新的可行性方案和思路。

基于随机增强Swin-Tiny Transformer的玉米病害识别及应用

针对图像识别中获取全局特征的局限性及难以提升识别准确性的问题,提出一种基于随机增强Swin-Tiny Transformer轻量级模型的图像识别方法.该方法在预处理阶段结合基于随机数据增强(random data augmentation based enhancement,RDABE)算法对图像特征进行增强,并采用Transformer的自注意力机制,以获得更全面的高层视觉语义信息.通过在玉米病害数据集上优化Swin-Tiny Transformer模型并进行参数微调,在农业领域的玉米病害上验证了该算法的适用性,实现了更精确的病害检测.实验结果表明,基于随机增强的轻量级Swin-Tiny+RDABE模型对玉米病害图像识别准确率达93.5867%.在参数权重一致,与性能优秀的轻量级Transformer、卷积神经网络(CNN)系列模型对比的实验结果表明,改进的模型准确率比Swin-Tiny Transformer,Deit3_Small,Vit_Small,Mobilenet_V3_Small,ShufflenetV2和Efficientnet_B1_Pruned模型提高了1.1877%~4.9881%,且能迅速收敛.

基于CCA和Transformer的YOLOv8船舶目标检测算法

为了提高利用合成孔径雷达图像进行船舶目标检测的精度、准确率和鲁棒性,提出了一种基于YOLOv8的改进算法:CCAT-YOLOv8。在CCAT-YOLOv8算法中,一方面设计了一种坐标通道注意力(coordinate channel attention,CCA)机制模块,用于降低检测受到港口建筑、海岸环境、船舶分布密度和外型大小等因素的影响,提高算法在复杂环境下的检测精度;另一方面基于Transformer网络提出了一种改进Transformer模块用于缓解图像噪点和光污染对检测的干扰,以增强模型对图片深层特征信息的挖掘能力,提升算法目标检测的准确率和可靠性。最后,面向中国资源卫星应用中心提供的船舶数据集对CCAT-YOLOv8算法进行了有效性检测,算法的平均精度为92.57%,准确率达到91.58%,较好地体现了CCAT-YOLOv8算法在船舶目标检测上的内在价值与应用潜力。

ResoNet:Robust and Explainable ENSO Forecasts with Hybrid Convolution and Transformer Networks

Recent studies have shown that deep learning(DL)models can skillfully forecast El Niño–Southern Oscillation(ENSO)events more than 1.5 years in advance.However,concerns regarding the reliability of predictions made by DL methods persist,including potential overfitting issues and lack of interpretability.Here,we propose ResoNet,a DL model that combines CNN(convolutional neural network)and transformer architectures.This hybrid architecture enables our model to adequately capture local sea surface temperature anomalies as well as long-range inter-basin interactions across oceans.We show that ResoNet can robustly predict ENSO at lead times of 19 months,thus outperforming existing approaches in terms of the forecast horizon.According to an explainability method applied to ResoNet predictions of El Niño and La Niña from 1-to 18-month leads,we find that it predicts the Niño-3.4 index based on multiple physically reasonable mechanisms,such as the recharge oscillator concept,seasonal footprint mechanism,and Indian Ocean capacitor effect.Moreover,we demonstrate for the first time that the asymmetry between El Niño and La Niña development can be captured by ResoNet.Our results could help to alleviate skepticism about applying DL models for ENSO prediction and encourage more attempts to discover and predict climate phenomena using AI methods.

基于Swin Transformer和YOLOv5的无纺布瑕疵检测

对无纺布进行瑕疵检测,可以帮助企业提升生产效率,节约成本,但是基于CNN的目标检测算法受限于卷积核的局部特性,缺乏对图像的全局建模,对尺度变化范围大的瑕疵检出效果不理想。因此,提出了基于Swin Transformer和YOLOv5的无纺布瑕疵检测方法,并引入了CBAM注意力机制,同时微调了预测目标框的anchor尺寸;在自制数据集上对所提方法的有效性进行了验证。结果表明,通过其强大的自我注意力对特征进行编码、解码,网络可以获得更大的感受野,充分联系上下文关系;Swin的基于特征金字塔的分层构建结构与YOLOv5的neck设计十分相似,可以帮助网络在多尺度特征图上对目标进行预测;网络对重要信息的关注度得到了提高;通过Mosaic和MixUp数据增强丰富了数据分布;模型的鲁棒性和对无纺布的检测性能得到提高,回归预测结果更精准。

Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer

Transformer-based models have facilitated significant advances in object detection.However,their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unmanned aerial vehicle(UAV)imagery.Addressing these limitations,we propose a hybrid transformer-based detector,H-DETR,and enhance it for dense small objects,leading to an accurate and efficient model.Firstly,we introduce a hybrid transformer encoder,which integrates a convolutional neural network-based cross-scale fusion module with the original encoder to handle multi-scale feature sequences more efficiently.Furthermore,we propose two novel strategies to enhance detection performance without incurring additional inference computation.Query filter is designed to cope with the dense clustering inherent in drone-captured images by counteracting similar queries with a training-aware non-maximum suppression.Adversarial denoising learning is a novel enhancement method inspired by adversarial learning,which improves the detection of numerous small targets by counteracting the effects of artificial spatial and semantic noise.Extensive experiments on the VisDrone and UAVDT datasets substantiate the effectiveness of our approach,achieving a significant improvement in accuracy with a reduction in computational complexity.Our method achieves 31.9%and 21.1%AP on the VisDrone and UAVDT datasets,respectively,and has a faster inference speed,making it a competitive model in UAV image object detection.

基于Transformer改进YOLOv5的交通标志检测算法

交通标志检测作为自动驾驶的组成部分直接影响着行车安全。针对现有算法对图像中尺寸小、被遮挡的标志存在漏检、误检的问题,文中提出了基于改进YOLOv5的交通标志检测算法。首先对原模型注意力缺失的问题经过对比后构建了BiFormer-y,使模型可以更好获取长期依赖;接着针对层数较深造成的具有丢失特征的缺陷,利用残差结构重新设计检测层,从而更好地保留特征;最后对耦合头的空间错位问题引入解耦头并进行优化。CCTSDB2021的实验表明,精确率、召回率、mAP分别为97.0、95.9、97.9与先进工作相比具有明显优势。

Stage IV malignant transformation of mature cystic teratoma palliatively treated with concurrent chemoradiotherapy:A case report

BACKGROUND Malignant transformation(MT)of mature cystic teratoma(MCT)has a poor prognosis,especially in advanced cases.Concurrent chemoradiotherapy(CCRT)has an inhibitory effect on MT.CASE SUMMARY Herein,we present a case in which CCRT had a reduction effect preoperatively.A 73-year-old woman with pyelonephritis was referred to our hospital.Computed tomography revealed right hydronephrosis and a 6-cm pelvic mass.Endoscopic ultrasound-guided fine-needle biopsy(EUS-FNB)revealed squamous cell carci-noma.The patient was diagnosed with MT of MCT.Due to her poor general con-dition and renal malfunction,we selected CCRT,expecting fewer adverse effects.After CCRT,her performance status improved,and the tumor size was reduced;surgery was performed.Five months postoperatively,the patient developed dis-semination and lymph node metastases.Palliative chemotherapy was ineffective.She died 18 months after treatment initiation.CONCLUSION EUS-FNB was useful in the diagnosis of MT of MCT;CCRT suppressed the disea-se and improved quality of life.

Transforming growth factor-beta 1 enhances discharge activity of cortical neurons

Transforming growth factor-beta 1(TGF-β1)has been extensively studied for its pleiotropic effects on central nervous system diseases.The neuroprotective or neurotoxic effects of TGF-β1 in specific brain areas may depend on the pathological process and cell types involved.Voltage-gated sodium channels(VGSCs)are essential ion channels for the generation of action potentials in neurons,and are involved in various neuroexcitation-related diseases.However,the effects of TGF-β1 on the functional properties of VGSCs and firing properties in cortical neurons remain unclear.In this study,we investigated the effects of TGF-β1 on VGSC function and firing properties in primary cortical neurons from mice.We found that TGF-β1 increased VGSC current density in a dose-and time-dependent manner,which was attributable to the upregulation of Nav1.3 expression.Increased VGSC current density and Nav1.3 expression were significantly abolished by preincubation with inhibitors of mitogen-activated protein kinase kinase(PD98059),p38 mitogen-activated protein kinase(SB203580),and Jun NH2-terminal kinase 1/2 inhibitor(SP600125).Interestingly,TGF-β1 significantly increased the firing threshold of action potentials but did not change their firing rate in cortical neurons.These findings suggest that TGF-β1 can increase Nav1.3 expression through activation of the ERK1/2-JNK-MAPK pathway,which leads to a decrease in the firing threshold of action potentials in cortical neurons under pathological conditions.Thus,this contributes to the occurrence and progression of neuroexcitatory-related diseases of the central nervous system.

A Comprehensive Survey of Recent Transformers in Image,Video and Diffusion Models

Transformer models have emerged as dominant networks for various tasks in computer vision compared to Convolutional Neural Networks(CNNs).The transformers demonstrate the ability to model long-range dependencies by utilizing a self-attention mechanism.This study aims to provide a comprehensive survey of recent transformerbased approaches in image and video applications,as well as diffusion models.We begin by discussing existing surveys of vision transformers and comparing them to this work.Then,we review the main components of a vanilla transformer network,including the self-attention mechanism,feed-forward network,position encoding,etc.In the main part of this survey,we review recent transformer-based models in three categories:Transformer for downstream tasks,Vision Transformer for Generation,and Vision Transformer for Segmentation.We also provide a comprehensive overview of recent transformer models for video tasks and diffusion models.We compare the performance of various hierarchical transformer networks for multiple tasks on popular benchmark datasets.Finally,we explore some future research directions to further improve the field.

基于Non stationary-CNN-Transformer的海浪有效波高预测

针对海浪有效波高序列波动性、随机性较强,难以精确预测以及模型无法高效挖掘深层特征间关系的问题,提出一种基于Non stationary-CNN-Transformer模型的海浪有效波高预测方法。首先,使用平稳化模块减弱海浪时序数据的非平稳性;其次,利用一维卷积神经网络(CNN)提取相关数据间的深层特征并构建特征向量;最后,使用含有平稳性注意力的Transformer描述波高序列的时间依赖性捕捉到序列之间的全局关系,通过逆归一化处理后获得有效波高预测结果。该方法可消除海浪时序数据的非平稳性,提升数据的预测效果,并具有优异的特征提取能力且善于处理大规模时间序列数据。在实验中应用澳大利亚的浮标实测数据,通过7组对比实验分别预测0.5、3、6、12和24 h的有效波高,对所提模型进行全方位、多角度的验证。算例研究结果表明,该文所提模型在不同时间段精度有明显提升。

Transformer-Based Cloud Detection Method for High-Resolution Remote Sensing Imagery

Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmentalmonitoring.Addressing the limitations of conventional convolutional neural networks,we propose an innovative transformer-based method.This method leverages transformers,which are adept at processing data sequences,to enhance cloud detection accuracy.Additionally,we introduce a Cyclic Refinement Architecture that improves the resolution and quality of feature extraction,thereby aiding in the retention of critical details often lost during cloud detection.Our extensive experimental validation shows that our approach significantly outperforms established models,excelling in high-resolution feature extraction and precise cloud segmentation.By integrating Positional Visual Transformers(PVT)with this architecture,our method advances high-resolution feature delineation and segmentation accuracy.Ultimately,our research offers a novel perspective for surmounting traditional challenges in cloud detection and contributes to the advancement of precise and dependable image analysis across various domains.

TransTM:A device-free method based on time-streaming multiscale transformer for human activity recognition

RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.

Transformer-based correction scheme for short-term bus load prediction in holidays

To tackle the problem of inaccurate short-term bus load prediction,especially during holidays,a Transformer-based scheme with tailored architectural enhancements is proposed.First,the input data are clustered to reduce complexity and capture inherent characteristics more effectively.Gated residual connections are then employed to selectively propagate salient features across layers,while an attention mechanism focuses on identifying prominent patterns in multivariate time-series data.Ultimately,a pre-trained structure is incorporated to reduce computational complexity.Experimental results based on extensive data show that the proposed scheme achieves improved prediction accuracy over comparative algorithms by at least 32.00%consistently across all buses evaluated,and the fitting effect of holiday load curves is outstanding.Meanwhile,the pre-trained structure drastically reduces the training time of the proposed algorithm by more than 65.75%.The proposed scheme can efficiently predict bus load results while enhancing robustness for holiday predictions,making it better adapted to real-world prediction scenarios.

Multiscale Fusion Transformer Network for Hyperspectral Image Classification

Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.

An Enhanced Multiview Transformer for Population Density Estimation Using Cellular Mobility Data in Smart City

This paper addresses the problem of predicting population density leveraging cellular station data.As wireless communication devices are commonly used,cellular station data has become integral for estimating population figures and studying their movement,thereby implying significant contributions to urban planning.However,existing research grapples with issues pertinent to preprocessing base station data and the modeling of population prediction.To address this,we propose methodologies for preprocessing cellular station data to eliminate any irregular or redundant data.The preprocessing reveals a distinct cyclical characteristic and high-frequency variation in population shift.Further,we devise a multi-view enhancement model grounded on the Transformer(MVformer),targeting the improvement of the accuracy of extended time-series population predictions.Comparative experiments,conducted on the above-mentioned population dataset using four alternate Transformer-based models,indicate that our proposedMVformer model enhances prediction accuracy by approximately 30%for both univariate and multivariate time-series prediction assignments.The performance of this model in tasks pertaining to population prediction exhibits commendable results.

Multivariate Time Series Anomaly Detection Based on Spatial-Temporal Network and Transformer in Industrial Internet of Things

In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.

Network Configuration Entity Extraction Method Based on Transformer with Multi-Head Attention Mechanism

Nowadays,ensuring thequality of networkserviceshas become increasingly vital.Experts are turning toknowledge graph technology,with a significant emphasis on entity extraction in the identification of device configurations.This research paper presents a novel entity extraction method that leverages a combination of active learning and attention mechanisms.Initially,an improved active learning approach is employed to select the most valuable unlabeled samples,which are subsequently submitted for expert labeling.This approach successfully addresses the problems of isolated points and sample redundancy within the network configuration sample set.Then the labeled samples are utilized to train the model for network configuration entity extraction.Furthermore,the multi-head self-attention of the transformer model is enhanced by introducing the Adaptive Weighting method based on the Laplace mixture distribution.This enhancement enables the transformer model to dynamically adapt its focus to words in various positions,displaying exceptional adaptability to abnormal data and further elevating the accuracy of the proposed model.Through comparisons with Random Sampling(RANDOM),Maximum Normalized Log-Probability(MNLP),Least Confidence(LC),Token Entrop(TE),and Entropy Query by Bagging(EQB),the proposed method,Entropy Query by Bagging and Maximum Influence Active Learning(EQBMIAL),achieves comparable performance with only 40% of the samples on both datasets,while other algorithms require 50% of the samples.Furthermore,the entity extraction algorithm with the Adaptive Weighted Multi-head Attention mechanism(AW-MHA)is compared with BILSTM-CRF,Mutil_Attention-Bilstm-Crf,Deep_Neural_Model_NER and BERT_Transformer,achieving precision rates of 75.98% and 98.32% on the two datasets,respectively.Statistical tests demonstrate the statistical significance and effectiveness of the proposed algorithms in this paper.