Camera style transformation with preserved self-similarity and domain-dissimilarity in unsupervised person re-identification

The inconsistency caused by different factors, such as different camera imaging methods, complex imaging environments, and changes in light, present a huge challenge to person re-identification (re-ID). Unsupervised domain adaptation (UDA) can solve the inconsistency issue to a certain extent, but different datasets may not have any overlapping of people’s identities. Therefore, it is necessary to pay attention to people’s identities in solving domain-dissimilarity. A camera imaging style transformation with preserved self-similarity and domain-dissimilarity (CSPSD) is proposed to solve the cross-domain issue in person re-ID. First, CycleGAN is applied to determine the style conversion between source and target domains. Intra-domain identity constraints are used to maintain identity consistency between source and target domains during the image style transformation process. Maximum mean difference (MMD) is used to reduce the difference in feature distribution between source and target domains. Then, a one-to-n mapping method is proposed to achieve the mapping between positive pairs and distinguish negative pairs. Any sample image from the source domain and its transformed image or a transformed image with the same identity information compose a positive pair. The transformed image and any image from the target domain compose a negative pair. Next, a circle loss function is used to improve the learning speed of positive and negative pairs. Finally, the proposed CSPSD that can effectively reduce the difference between domains and an existing feature learning network work together to learn a person re-ID model. The proposed method is applied to three public datasets, Market-1501, DukeMTMC-reID, and MSMT17. The comparative experimental results confirm the proposed method can achieve highly competitive recognition accuracy in person re-ID.     

基于多尺度加权特征融合的行人重识别方法研究

针对目前由于行人重识别普遍存在的遮挡以及多姿态变化等原因,导致的行人重识别率低的问题,提出一种基于多尺度加权特征融合的行人重识别方法（Person Re-identification Method Based on Multi-scale Weighted Feature Fusion,MSWF）。该方法首先使用基准网络ResNeSt-50提取图像特征,获得下采样3倍、下采样4倍和下采样5倍的特征图,输入到加权特征金字塔网络中,然后使用快速归一化融合方法进行特征融合,在特征融合中引入加权操作可以让模型在训练过程中学习如何给融合特征的权重值进行分配,这样可以充分利用不同尺度的特征,获得更加丰富的行人特征。最后将融合后的富含语义信息的高层特征作为全局特征,将融合后的高分辨率特征作为局部特征。在训练过程中,联合Softmax分类损失函数、三元组损失函数和中心损失函数对模型进行训练,在测试阶段,将全局特征和局部特征沿通道维度进行拼接表示行人特征,并使用欧氏距离计算行人之间的距离。该方法在Market-1501、DukeMTMC-reID、CUHK03-Labeled和CUHK03-Detect...     

Multiscale Global-Aware Channel Attention for Person Re-identification

Most person re-identification methods are researched under various assumptions. However, viewpoint variations or occlusions are often encountered in practical scenarios. These are prone to intra-class variance. In this paper, we propose a multiscale global-aware channel attention (MGCA) model to solve this problem. It imitates the process of human visual perception, which tends to observe things from coarse to fine. The core of our approach is a multiscale structure containing two key elements: the global-aware channel attention (GCA) module for capturing the global structural information and the adaptive selection feature fusion (ASFF) module for highlighting discriminative features. Moreover, we introduce a bidirectional guided pairwise metric triplet (BPM) loss to reduce the effect of outliers. Extensive experiments on Market-1501, DukeMTMC-reID, and MSMT17, and achieve the state-of-the-art results on mAP. Especially, our approach exceeds the current best method by 2.0% on the most challenging MSMT17 dataset.     

Grafted network for person re-identification

Convolutional neural networks have shown outstanding effectiveness in person re-identification (re-ID). However, the models always have large number of parameters and much computation for mobile application. In order to relieve this problem, we propose a novel grafted network (GraftedNet), which is designed by grafting a high-accuracy rootstock and a light-weighted scion. The rootstock is based on the former parts of ResNet-50 to provide a strong baseline, while the scion is a new designed module, composed of the latter parts of SqueezeNet, to compress the parameters. To extract more discriminative feature representation, a joint multi-level and part-based feature is proposed. In addition, to train GraftedNet efficiently, we propose an accompanying learning method, by adding an accompanying branch to train the model in training and removing it in testing for saving parameters and computation. On three public person re-ID benchmarks (Market1501, DukeMTMC-reID and CUHK03), the effectiveness of GraftedNet is evaluated and its components are analyzed. Experimental results show that the proposed GraftedNet achieves 93.02%, 85.3% and 76.2% in Rank-1 and 81.6%, 74.7% and 71.6% in mAP, with only 4.6M parameters.     

MTNet: Mutual tri-training network for unsupervised domain adaptation on person re-identification

The existing unsupervised domain adaptation (UDA) methods on person re-identification (re-ID) often employ clustering to assign pseudo labels for unlabeled target domain samples. However, it is difficult to give accurate pseudo labels to unlabeled samples in the clustering process. To solve this problem, we propose a novel mutual tri-training network, termed MTNet, for UDA person re-ID. The MTNet method can avoid noisy labels and enhance the complementarity of multiple branches by collaboratively training the three different branch networks. Specifically, the high-confidence pseudo labels are used to update each network branch according to the joint decisions of the other two branches. Moreover, inspired by self-paced learning, we employ a sample filtering scheme to feed unlabeled samples into the network from easy to hard, so as to avoid trapping in the local optimal solution. Extensive experiments show that the proposed method can achieve competitive performance compared with the state-of-the-art person re-ID methods.     

基于域鉴别网络和域自适应的行人重识别

针对行人重识别无监督跨域迁移问题,提出一种 基于域鉴别网络和域自适应的行人重识别算法。首先,使用改 进ResNet-50训练监督域鉴别网络模型,加入共享空间组件得到特征 不变属性,用于区分类间图像,并基 于对比损失和差异损失来提高模型的分类性能。其次,利用域自适应无监督迁移方法由源域 数据集导出特 征不变属性,并应用到未标记的目标域数据集上。最后,匹配查询图像和共享空间中的图库 图像执行跨域 行人重识别。为验证算法有效性,在CUHK03、Market-1501和DukeMTMC-reID数据集上进行了实验,算法 在Rank-1准确度分别达到34.1%、38.1%和28.3%,在mAP分别达到34.2%、17. 1%和17.5%,最后还验证了 模型各个组件在训练阶段的必要性。结果表明本文算法在大规模数据集上的性能优于现有的 一些无监督行人重识别方法,甚至接近于某些传统监督学习方法的性能。     

基于多尺度和注意力融合学习的行人重识别

行人重识别的关键依赖于行人特征的提取,卷积神经网络具有强大的特征提取以及表达能力。针对不同尺度下可以观察到不同的特征,该文提出一种基于多尺度和注意力网络融合的行人重识别方法(MSAN)。该方法通过对网络不同深度的特征进行采样,将采样的特征融合后对行人进行预测。不同深度的特征图具有不同的表达能力,使网络可以学习到行人身上更加细粒度的特征。同时将注意力模块嵌入到残差网络中,使得网络能更加关注于一些关键信息,增强网络特征学习能力。所提方法在Market1501, DukeMTMC-reID和MSMT17_V1数据集上首位准确率分别到了95.3%, 89.8%和82.2%。实验表明,该方法充分利用了网络不同深度的信息和关注的关键信息,使模型具有很强的判别能力,而且所提模型的平均准确率优于大多数先进算法。     

Layer‐wise hint‐based training for knowledge transfer in a teacher‐student framework

We devise a layer‐wise hint training method to improve the existing hint‐based knowledge distillation (KD) training approach, which is employed for knowledge transfer in a teacher‐student framework using a residual network (ResNet). To achieve this objective, the proposed method first iteratively trains the student ResNet and incrementally employs hint‐based information extracted from the pretrained teacher ResNet containing several hint and guided layers. Next, typical softening factor‐based KD training is performed using the previously estimated hint‐based information. We compare the recognition accuracy of the proposed approach with that of KD training without hints, hint‐based KD training, and ResNet‐based layer‐wise pretraining using reliable datasets, including CIFAR‐10, CIFAR‐100, and MNIST. When using the selected multiple hint‐based information items and their layer‐wise transfer in the proposed method, the trained student ResNet more accurately reflects the pretrained teacher ResNet's rich information than the baseline training methods, for all the benchmark datasets we consider in this study.     

基于通道注意力机制和多尺度卷积的行人重识别

针对真实环境中由于复杂背景和物体遮挡、角度变换、行人姿态变化带来的行人重识别(person re-identification,person re-ID) 问题,设计了基于通道注意力(efficient channel attention,ECA) 机制和多尺度卷积(poly-scale convolution,PSConv) 的行人重识别模型。首先利用残差网络提取全局特征,在网络末端加入基于ECA机制及PSConv的特征融合模块,将全局特征和该模块提取的全局特征进行融合,之后将新的全局特征进行分割得到局部特征,最后将新的全局特征和分割得到的局部特征融合得到最终特征,并计算损失函数。模型在Market1501和DukeMTMC-reID 数据集上进行实验验证。在Market1501数据集中,Rank-1和平均精度均值分别达到94.3%和85.2%,在DukeMTMC-reID数据集中,上述两参数分别达到86.3%和75.4%。实验结果可知,该模型可应对实际环境中的复杂情况,增强行人特征的辨别力,有效提高行人重识别的准确率和精度。     

DDFP:A data driven filter pruning method with pruning compensation

Neural network pruning techniques can be effective in accelerating neural network models, making it possible to deploy them on edge devices. In this paper, we propose to prune neural networks using data variance. Unlike other existing methods, this method is somewhat robust and does not invalidate our criteria depending on the number of data batches and the number of training sessions. We also propose a pruning compensation technique. This technique fuses the pruned convolutional information into the remaining convolutional kernel close to it. This fusion operation can effectively help retain the pruned information. We evaluate the proposed method on a number of standard datasets and compare it with several current state-of-the-art methods. Our method always achieves better performance. For example, on Tiny ImageNet, our method can prune 54.2% FLOPs of ResNet50 while obtaining a 0.22% accuracy improvement.     

基于残差网络和注意力机制的步态识别算法

针对现有行人步态数据集样本较少、多特征融合复杂且识别精准度不高的问题,提出了一种基于残差网络和注意力机制的步态识别算法。首先对每种特征制作标签,然后将表示不同特征的标签做拼接,达到识别多特征的目的。通过迁移ResNet18的预训练模型,并在ResNet18网络第一个和最后一个卷积层后面加入注意力机制,能够加速网络的收敛,提升模型的精准率。〖JP3〗在CASIA-B数据集上进行多次实验,结果表明所提出方法能准确识别行人、状态和不同角度三种步态特征,识别的精准率为97.6%。     

基于改进YOLOX的X射线违禁物品检测

在安全检查过程中快速准确地识别违禁物品有利于维护公共安全。针对X射线行李图像中存在的物品堆叠变形、复杂背景干扰、小尺寸违禁物品检测等问题,提出一种改进模型用于违禁物品检测。改进基于YOLOX模型进行,首先在主干网络中引入注意力机制加强神经网络对违禁品的感知能力;其次在Neck部分改进多尺度特征融合方式,在特征金字塔结构后加入Bottom-up结构,增强网络细节表现能力以此提高对小目标的识别率;最后针对损失函数计算的弊端改进IOU损失的计算方式,并根据违禁物品检测任务特点改进各类损失函数的权重,增大对网络误判的惩罚来优化模型。使用该改进模型在SIXray数据集上进行实验,m AP达到89.72%,FPS到达111.7 frame/s具备快速性和有效性,所提模型与阶段主流模型相比准确率和检测速度都有所提升。     

引入自上向下特征融合的小目标检测算法

针对原始SSD(Single Shot Multibox Detector)算法未充分利用各特征层之间关系导致浅层特征层缺乏小目标语义信息的问题,为了提高对小目标的检测能力,提出了一种结合PANet多尺度特征融合网络和自上向下特征融合路径的TTB-SSD(Top to Bottom SSD)改进算法。首先,使用PANet多尺度特征融合网络对特征进行反复提取,从而获得丰富的多尺度语义信息;然后,使用一种深层特征融合模块将浅层特征层的空间信息传递到深层特征层,进而更准确地对小目标进行定位;最后,为了增强浅层特征层的语义信息,构造了自上向下的特征融合路径,从而强化浅层对小目标检测的准确率。实验结果表明,在PASCAL VOC2007测试集检测的mAP(Mean Average Precision)值达到80.5%,对目标的mAP较原始SSD提高了5.7%,证明了该算法对小目标检测的有效性。     

红外与可见光图像多特征自适应融合方法

由于成像机理不同,红外图像以像素分布表征典型目标,而可见光图像以边缘和梯度描述纹理细节,现有的融合方法不能依据源图像特征自适应变化,造成融合结果不能同时保留红外目标特征与可见光纹理细节。为此,本文提出红外与可见光图像多特征自适应融合方法。首先,构建了多尺度密集连接网络,可以有效聚合所有不同尺度不同层级的中间特征,利于增强特征提取和特征重构能力。其次,设计了多特征自适应损失函数,采用VGG-16网络提取源图像的多尺度特征,以像素强度和梯度为测量准则,以特征保留度计算特征权重系数。多特征自适应损失函数监督网络训练,可以均衡提取源图像各自的特征信息,从而获得更优的融合效果。公开数据集的实验结果表明,该方法在主、客观评价方面均优于其他典型方法。     

基于特征增强的模糊红外刑侦目标提取算法研究

本研究旨在解决红外图像刑侦场景中目标边缘模糊和轮廓不完整等问题。提出了一种基于特征增强的模糊刑侦目标提取方法。首先,设计模糊刑侦目标边缘提取网络模型(Blurry Criminal Investigation Target Edge Extraction Network Combined with Spatial Channel Attention, BCES-Net),并利用空间通道关注模块(Spatial and Channel Attention Module, STCAM)获取具有强语义信息的特征图像。接着通过建模提取来获取包含语义类别信息的边缘特征和模糊刑侦目标特征。在训练过程中,基于特定损失函数和多种特征融合技术,通过反复监督学习和训练校正,提高了边缘和模糊刑侦目标分割性能。在手部热痕迹数据集上,与DeeplabV3+、U-Net、HRNet、PSPNet等模型相比,BCES-Net模型在均交并比(mean Intersection over Union, mIoU)、平均精度均值(mean Average Precision, mAP)、准确率等评价指标上显著优越,mIo...     

Exploiting multigranular salient features with hierarchical multi-mode attention network for pedestrian re-IDentification

In this paper, we propose an end-to-end hierarchical-based multi-mode attention network and adaptive fusion (HMAN-HAF) strategy to learn different-level salient features for re-ID tasks. First, according to each layer’s characteristics, a hierarchical multi-mode attention network (HMAN) is designed to adopt different attention models for different-level salient feature learning. Specifically, refined channel-wise attention (CA) is adopted to capture high-level valuable semantic information, an attentive region model (AR) is used to detect salient regions in the low layer, and fused attention (FA) is designed to capture the salient regions of valuable channels in the middle layer. Second, a hierarchical adaptive fusion (HAF) is constructed to fulfill the complementary strengths of different-level salient features. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods on the following challenging benchmarks: Market-1501, DukeMTMC-reID and CUHK03.     

双金字塔结构引导的多粒度行人重识别方法北大核心CSCD

针对杂乱场景下难以有效地提取行人关键信息和局部遮挡时全局特征方法失效的问题,提出了一种双金字塔结构引导的多粒度行人重识别(person re-identification,ReID)方法。首先在ResNet50中嵌入注意力金字塔,引导网络由粗到细依次挖掘不同粒度的特征,使网络更倾向于关注复杂环境中行人的显著区域;其次通过结构不对称的双重注意力特征金字塔分支(double attention feature pyramid branch,DFP branch)提取多尺度的行人特征,丰富特征的多样性,同时双重注意力机制可使分支从浅层信息中捕获高细粒度的局部特征;最后将粒度较粗的全局特征与多层级细粒度的局部特征融合,两种金字塔相互作用,以此获得更多具有鉴别性的多粒度特征,改善行人遮挡问题。在多个数据集上进行了实验,结果表明,各项评价指标均高于目前大多数主流模型,其中在DukeMTMC-reID数据集上,Rank-1、mAP和平均逆负处罚(mean inverse negative penalty,mINP)分别达到了91.6%、81.9%、48.1%。     

多通道时空融合网络双人交互行为识别

提出一种基于多通道时空融合网络的双人交互行为识别方法,对双人骨架序列行为进行识别。首先,采用视角不变性特征提取方法提取双人骨架特征,然后,设计两层级联的时空融合网络模型,第一层基于一维卷积神经网络（1DCNN）和双向长短时记忆网络（BiLSTM）学习空间特征,第二层基于长短时记忆网络(LSTM)学习时间特征,得到双人骨架的时空融合特征。最后,采用多通道时空融合网络分别学习多组双人骨架特征得到多通道融合特征,利用融合特征识别交互行为,各通道之间权值共享。将文中算法应用于NTU-RGBD人体交互行为骨架库,双人交叉对象实验准确率可达96.42%,交叉视角实验准确率可达97.46%。文中方法与该领域的典型方法相比,在双人交互行为识别中表现出更好的性能。     

Segmentation mask guided end-to-end person search

Person search aims to search for a target person among multiple images recorded by multiple surveillance cameras, which faces various challenges from both pedestrian detection and person re-identification. Besides the large intra-class variations owing to various illumination conditions, occlusions and varying poses, background clutters in the detected pedestrian bounding boxes further deteriorate the extracted features for each person, making them less discriminative. To tackle these problems, we develop a novel approach which guides the network with segmentation masks so that discriminative features can be learned invariant to the background clutters. We demonstrate that joint optimization of pedestrian detection, person re-identification and pedestrian segmentation enables to produce more discriminative features for pedestrian, and consequently leads to better person search performance. Extensive experiments on two widely used benchmark datasets prove the superiority of our approach. In particular, our proposed model achieves the state-of-the-art performance (86.3% mAP and 86.5% top-1 accuracy) on CUHK-SYSU dataset.     

基于改进SSD的X光图像管制刀具检测与识别

以安检X光图像管制刀具自动检测识别系统为研究对象,针对原始SSD(Single Shot MultiBox Detector)算法对浅层特征图表征能力不强,在训练阶段小目标特征逐渐消失,检测精度与实时性不佳,存在对安检危险品中管制刀具等小目标漏检误检等问题,从两个方面对原始SSD进行改进:一方面,用抗退化性能更强的ResNet34网络替换SSD中的基础网络VGG16,构建SSD-ResNet34网络模型,对基础网络后三层作卷积并进行轻量级网络融合,形成新的低层特征图;将网络部分扩展层作反卷积,形成新的高层特征图。另一方面,采用跳跃连接的方式将高层特征图和低层特征图进行多尺度特征融合。经实验分析,改进后的算法对X光图像管制刀具等小目标的检测精度和速度均有明显提升,且算法鲁棒性好,实时性良好。在VOC2007+2012通用数据集上,改进SSD算法的检测精度比SSD算法高1.7%,达到了80.5%。