Person Re-identification Methods Research Articles

Enhancing Person Re-Identification through Attention-Driven Global Features and Angular Loss Optimization.

To address challenges related to the inadequate representation and inaccurate discrimination of pedestrian attributes, we propose a novel method for person re-identification, which leverages global feature learning and classification optimization. Specifically, this approach integrates a Normalization-based Channel Attention Module into the fundamental ResNet50 backbone, utilizing a scaling factor to prioritize and enhance key pedestrian feature information. Furthermore, dynamic activation functions are employed to adaptively modulate the parameters of ReLU based on the input convolutional feature maps, thereby bolstering the nonlinear expression capabilities of the network model. By incorporating Arcface loss into the cross-entropy loss, the supervised model is trained to learn pedestrian features that exhibit significant inter-class variance while maintaining tight intra-class coherence. The evaluation of the enhanced model on two popular datasets, Market1501 and DukeMTMC-ReID, reveals improvements in Rank-1 accuracy by 1.28% and 1.4%, respectively, along with corresponding gains in the mean average precision (mAP) of 1.93% and 1.84%. These findings indicate that the proposed model is capable of extracting more robust pedestrian features, enhancing feature discriminability, and ultimately achieving superior recognition accuracy.

Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification.

Supervised person re-identification (re-id) methods require expensive manual labeling costs. Although unsupervised re-id methods can reduce the requirement of the labeled datasets, the performance of these methods is lower than the supervised alternatives. Recently, some weakly supervised learning-based person re-id methods have been proposed, which is a balance between supervised and unsupervised learning. Nevertheless, most of these models require another auxiliary fully supervised datasets or ignore the interference of noisy tracklets. To address this problem, in this work, we formulate a weakly supervised tracklet association learning (WS-TAL) model only leveraging the video labels. Specifically, we first propose an intra-bag tracklet discrimination learning (ITDL) term. It can capture the associations between person identities and images by assigning pseudo labels to each person image in a bag. And then, the discriminative feature for each person is learned by utilizing the obtained associations after filtering the noisy tracklets. Based on that, a cross-bag tracklet association learning (CTAL) term is presented to explore the potential tracklet associations between bags by mining reliable positive tracklet pairs and hard negative pairs. Finally, these two complementary terms are jointly optimized to train our re-id model. Extensive experiments on the weakly labeled datasets demonstrate that WS-TAL achieves 88.1% and 90.3% rank-1 accuracy on the MARS and DukeMTMC-VideoReID datasets respectively. The performance of our model surpasses the state-of-the-art weakly supervised models by a large margin, even outperforms some fully supervised re-id models.

ReFID: Reciprocal Frequency-aware Generalizable Person Re-identification via Decomposition and Filtering

Domain generalization of person re-identification aims to conduct testing across domains that have not been previously encountered, without utilizing target domain data during the training stage. As the number of source domains increases, the relationships between training samples become more complex. This can lead to domain-invariant features that include certain instance-level spurious correlations, which can impact the model’s ability to generalize further. To overcome this limitation, the Reciprocal Frequency-aware Generalizable Person Re-identification method is proposed in this article, which aims to utilize spectral feature correlation learning to transmit frequency component information and generate more discriminative hybrid features. A module called Bilateral Frequency Component-guided Attention is developed to help the network understand high-level semantic and texture information from various frequency features. Furthermore, to reduce the impact of noise from the frequency domain, this article proposes an innovative module called Fourier Noise Masquerade Filtering. This module enhances the portability of frequency domain components while simultaneously suppressing elements that do not contribute to generalization. Extensive experimental results on various datasets demonstrate that our method is effective and superior to the state-of-the-art methods.

Instance-aware diversity feature generation for unsupervised person re-identification

Unsupervised person re-identification (Re-ID) methods have made significant progress by exploiting contrastive learning from unlabeled data. However, the previous approaches including cluster-level or instance-level contrast loss, did not fully explore inherent commonality of each identified individual from unlabeled samples, where the divergence of individual cluster and convergence of different clusters leads to a set of noisy pseudo labels which may result in label noise accumulation. To address this issue, we propose an instance-aware diversity feature generation (IDFG) framework, which can form a stable clustering feature space by exhuming diverse counterparts of given exemplars to update memory dictionary of each cluster, so as to reduce the effect of noisy labels. Specifically, we combines instance segmentation and masked auto-encoder to generate foreground-invariant diversity counterparts of given exemplars to reduce inter-class convergence caused by background similarity between different identification instances. Further, we introduce an instance-aware diversity feature mining module, which gradually creates more reliable clusters to generate more robust pseudo labels by exploiting the compactness and independence of clustering to update the memory dictionary. Extensive experiments demonstrate that the proposed IDFG framework achieves impressive performances of 85.6%, 73.7%, and 31.0% mAP on Market1501, DukeMTMC-reID and MSMT17, respectively.

Exploring modality enhancement and compensation spaces for visible-infrared person re-identification

Visible-infrared person re-identification (VI-ReID) is a challenging task in computer vision due to the substantial modality gaps between visible and infrared images. The currently existing approaches can improve performance by addressing cross-modality discrepancies, but they often fail to generate compensation features that fully utilize the unique information present in each modality. Additionally, these methods mainly focus on pixel-level fusion of images, disregarding the challenge of modality misalignment. To address these issues, we propose a novel visible-infrared person re-identification method that explores modality enhancement and compensation spaces to extract more discriminative modality information. Furthermore, we introduce a modality mutual guidance strategy incorporating identity information mutual learning loss and modality-guided alignment loss, which can effectively leverage learned identity-related feature to guide alignment between visible and infrared modalities. Extensive experiments on public datasets demonstrate the significant superiority of our proposed method over existing state-of-the-art approaches.

Person re-identification method based on fine-grained feature fusion and self-attention mechanism

Person re-identification method based on fine-grained feature fusion and self-attention mechanism

Doubly stochastic subdomain mining with sample reweighting for unsupervised domain adaptive person re-identification

Clustering-based unsupervised domain adaptive person re-identification methods have achieved remarkable progress. However, existing works are easy to fall into local minimum traps due to the optimization of two variables, feature representation and pseudo labels. Besides, the model can also be hurt by the inevitable false assignment of pseudo labels. In order to solve these problems, we propose the Doubly Stochastic Subdomain Mining (DSSM) to prevent the nonconvex optimization from falling into local minima in this paper. And we also design a novel reweighting algorithm based on the similarity correlation coefficient between samples which is referred to as Maximal Heterogeneous Similarity (MHS), it can reduce the adverse effect caused by noisy labels. Extensive experiments on two popular person re-identification datasets demonstrate that our method outperforms other state-of-the-art works. The source code is available at https://github.com/Tchunansheng/DSSM.

An Orientation-Aware Attention Network for Person Re-Identification

Humans always identify persons through their characteristics, salient attributes, and these attributes’ locations on the body. Most person re-identification methods focus on global and local features corresponding to the former two discriminations, cropping person images into horizontal strips to obtain coarse locations of body parts. However, discriminative clues corresponding to location differences cannot be discovered, so persons with similar appearances are often confused because of their alike components. To address the above problem, we introduce pixel-wise relative positions for the invariance of their orientations in viewpoint changes. To cope with the scale change of relative position, we combine relative positions with self-attention modules that perform on multi-level features. Moreover, in the data augmentation stage, mirrored images are given new labels due to the conversion of the relative position along a horizontal orientation and change in visual chirality. Extensive experiments on four challenging benchmarks demonstrate that the proposed approach shows its superiority and effectiveness in discovering discriminating features.

Learning dual attention enhancement feature for visible–infrared person re-identification

Most previous visible–infrared person re-identification methods emphasized learning modality-shared features to narrow the modality differences, while neglecting the benefits of modality-specific features for feature embedding and narrowing the modality gap. To tackle this issue, our paper designs a method based on dual attention enhancement features to use shallow and deep features simultaneously. We first convert visible images into gray images to alleviate the visual difference. Then, to close the difference between modalities by learning the modality-specific features, we design a shallow feature measurement module, in which we use a class-specific maximum mean discrepancy loss to measure the distribution difference of specific features between two modalities. Finally, we design a dual attention feature enhancement module, which aims to mine more useful context information from modality-shared features to shorter the distance between classes within modalities. Specifically, our model exceeds the current SOTAs on SYSU-MM01, with 66.61% Rank-1 accuracy and 62.86% mAP.

Context-aided unicity matching for person re-identification

Most existing person re-identification methods compute the matching relations between person images based on the similarity ranking. It lacks the global viewpoint and context consideration, inevitably leading to ambiguous matching results and sub-optimal performance. Based on a natural assumption that images belonging to the same identity should not match with images belonging to different identities across views, called the unicity of person matching on the identity level, we propose an end-to-end person unicity matching architecture to learn and refine the person matching relations. We first employ the image samples’ context in feature space to generate the initial soft matchings using graph neural networks, and then utilize the samples’ global context to refine the soft matchings and reach the matching unicity by bipartite graph matching. Considering real-world applications, we further develop a fast algorithm without losing performance. Experimental results on five public benchmarks show the superiority of the proposed method.

Multiple-local feature and attention fused person re-identification method

Person re-identification (ReID) is widely used in intelligent security, monitoring, criminal investigation and other fields. Aiming at the problems of local occlusion, scale misalignment and attitude change of pedestrian images in actual scenes, we propose a Multi-local Feature and Attention fused network (MFA) used for person re-identification task. Firstly, Channel Point Affinity Attention module (CPAA) is embedded in the backbone network to enhance the ability of the network for extracting local details. The feature map output from the backbone network is horizontally segmented into four local feature maps, and further four branch networks are concatenated to the feature map of the backbone network. The four local feature maps are used to guide the four branch networks to pay more attention on different areas of pedestrians through Global Local Aligned loss (GLA) function. Finally, the pedestrian feature vector containing multi-local features is obtained. The mAP of the network on Market-1501, DukeMTMC-reID,CUHK03 and MSMT17 datasets were 88.6%, 81.4%, 79.5% and 64.7%, and the Rank-1 was 95.8%, 90.1%, 81.2% and 84.1% respectively. In addition, the model also obtained 73.2% and 68.1% of Rank-1 on partial dataset Patial-REID and Patial-iLIDS, respectively. Recently, The MFA model parameter is 28.3M and the inference efficiency is approximately 32 fps to an image with a resulation of 256 × 128. Compared with other ReID methods, our proposed methods achieved a competitive performance for ReID task. The code was available at github:git@github.com:ISCLab-Bistu/MFA.git.

Dual-stream feature fusion network for person re-identification

Person re-identification (Re-ID) has made significant progress in recent years. However, it still faces numerous challenges in real scenarios. Although researchers have proposed various solutions, the issue of similar clothing colors remains an obstacle in improving the performance of person re-identification. To solve this issue, we propose a dual-stream feature fusion network (DSFF-Net) to extract discriminative features from pedestrian images in two color spaces. Specifically, a dual-stream network is designed to extract RGB global features, grayscale global features, and local features of pedestrian images to increase the richness of pedestrian representations. A channel attention module is designed to direct the network to focus on the salient features of pedestrians. An embedding mixed pooling is designed, which integrates the outputs of global average pooling (GAP) and global max pooling (GMP) to obtain more discriminative global features. Besides, it can also remove redundant information and increase the discrimination of pedestrian representations. A fine-grained local feature embedding fusion operation is designed to obtain more discriminative local features by embedding and fusing fine-grained local features of RGB and grayscale pedestrian images. Since the final pedestrian representation fuses both global features and fine-grained discriminative features in RGB and grayscale spaces, DSFF-Net increases the discriminative capability and richness of pedestrian representations. Moreover, we conduct extensive experiments on three datasets, Market-1501 DukeMTMC-Reid, and CUHK03, and our method achieves the Rank-1/mAP of 95.9%/89.1%, 89.0%/79.2%, and 81.2%/78.7%, respectively. Experimental results show that the performance of DSFF-Net is better than those of most of the state-of-the-art person Re-ID methods.

Person Reidentification Based on Adaptive Relation Attention Network in Intelligent Monitoring System for the IoB

The Internet of Behavior (IoB), which combines Internet of Things and artificial intelligence, plays an important role in building smart city. As a significant part of data collection and analysis, intelligent monitoring system needs robust algorithms for analyzing data to make corresponding feedback. The development of person reidentification (re-id) has benefited from deep learning methods, especially for the IoB application. However, most existing person re-id methods under intelligent monitoring cannot solve some problems in the real world, such as occlusion and background cluster. In this article, we propose an adaptive relation attention (ARA) network for person re-id based on the ARA mechanism, which can address the abovementioned challenges effectively. The ARA module consists of relation branch and adaption branch. Relation branch captures the global structural information by mining relation among feature nodes. Adaption branch generates dynamic weights for attention features that relation branch produced. Our constructed intelligent IoB system can acquire the behavior status of pedestrian at different times and places, providing corresponding feedback rapidly. Data transmission and storage in our system are built in a decentralized way, which is based on blockchain. Our person re-id method outperforms many state-of-the-art methods on the CUHK03, Market-1501, and DukeMTMC-reID, showing excellent robustness.

Illumination Distillation Framework for Nighttime Person Re-Identification and a New Benchmark

Nighttime person Re-ID (person re-identification in the nighttime) is a very important and challenging task for visual surveillance but it has not been thoroughly investigated. Under the low illumination condition, the performance of person Re-ID methods usually sharply deteriorates. To address the low illumination challenge in nighttime person Re-ID, this paper proposes an Illumination Distillation Framework (IDF), which utilizes illumination enhancement and illumination distillation schemes to promote the learning of Re-ID models. Specifically, IDF consists of a master branch, an illumination enhancement branch, and an illumination distillation module. The master branch is used to extract the features from a nighttime image. The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features. However, nighttime and enhanced features usually contain data noise due to unstable lighting conditions and enhancement failures. To fully exploit the complementary benefits of nighttime and enhanced features while suppressing data noise, we propose an illumination distillation module. In particular, the illumination distillation module fuses the features from two branches through a bottleneck fusion model and then uses the fused features to guide the learning of both branches in a distillation manner. In addition, we build a real-world nighttime person Re-ID dataset, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Night600</i> , which contains 600 identities captured from different viewpoints and nighttime illumination conditions under complex outdoor environments. Experimental results demonstrate that our IDF can achieve state-of-the-art performance on two nighttime person Re-ID datasets ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Night600</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Knight</i> ). We will release our code and dataset at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Alexadlu/IDF</uri> .

Relation-Preserving Feature Embedding for Unsupervised Person Re-Identification

Some unsupervised approaches have been proposed recently for the person re-identification (ReID) problem since annotations of samples across cameras are time-consuming. However, most of these methods focus on the appearance content of the sample itself, and thus seldom take the structure relations among samples into account when learning the feature representation, which would provide a valuable guide for learning the representations of the samples. Thus hard samples may not be well solved due to the limited or even misleading information of the sample itself. To address this issue, in this paper, we propose a Relation-Preserving Feature Embedding (RPE) model that leverages structure relations among samples to boost the performance of the unsupervised person ReID methods without requiring any sample annotations. RPE aims at integrating the sample content and the neighborhood structure relations among samples into the learning of feature embeddings by combining the advantages of the autoencoder and graph autoencoder. Specifically, a relation and content information fusion (RCIF) module is proposed to dynamically merge the information from both perspectives of content and relation levels for feature embedding learning. Also, due to the lack of the identity labels of samples, we adopt an adaptive optimization strategy to update the affinity relations among samples instead of the reconstruction of the whole affinity matrix for optimizing the RPE model, which is more suitable for the unsupervised ReID task. Rigorous experiments on three widely-used large-scale benchmarks for person ReID demonstrate the superiority of the proposed method over current state-of-the-art unsupervised methods.

Co-segmentation assisted cross-modality person re-identification

We present a deep learning-based method for Visible-Infrared person Re-Identification (VI-ReID). The major contribution lies in the incorporation of co-segmentation into a multi-task learning framework for VI-ReID, where the co-segmentation concept aids in making the distributions of RGB images and IR images the same for the same identity but diverse for different identities. Accordingly, a novel multi-task learning based model, i.e., co-segmentation assisted VI-ReID (CSVI), is proposed in this paper. Specifically, the co-segmentation network first takes as the inputs the modality-shared features extracted from a set of RGB and IR images by using the VI-ReID model. Then, it exploits their semantic similarities for predicting the person masks of the common identities within the input RGB and IR images by using a cross-modality center based weight generation module and a segmentation decoder. Doing so enables the VI-ReID model to extract more additional modality-shared shape features for boosting performance. Meanwhile, the co-segmentation network implicitly establishes the interactions among the set of RGB and IR images, thus further bridging the large modality discrepancies. Our model’s effectiveness and superiority are verified through experimental comparisons with state-of-the-art algorithms on several benchmark datasets.

A visible-infrared clothes-changing dataset for person re-identification in natural scene

Person re-identification (Re-ID) has been widely used in intelligent surveillance systems, aiming at retrieving specific pedestrian images across different cameras. Although existing person Re-ID methods have achieved inspiring success, there are still limitations in practical monitoring system applications. To narrow the gap with the practical application, we introduce the cross-modality person Re-ID problem in the clothes-changing scene. Meanwhile, we construct the first Visible-Infrared Clothes-Changing (NEU-VICC) dataset, which contained 16632 RGB images and 8374 infrared images of 107 pedestrians. The critical challenge of the cross-modality person Re-ID problem in the clothes-changing scene lies in the vast modality discrepancy and the intra-class discrepancy caused by changing clothes. So, we propose a novel Semantic-Constraint Clothes-Changing Augmentation Network (SC3ANet) based on current cross-modality person Re-ID methods to solve this problem. Specifically, we design a semantic-constraint clothes-changing module that guides the model to learn clothes-irrelevant features by randomly changing pedestrians' clothes. In addition, we devise a dual-granularity constraint loss module to mitigate inter-modality and intra-class differences. Experiments on our NEU-VICC dataset show that the SC3ANet achieves the best results. The dataset and code are available at: https://github.com/VDT-2048/NEU-VICC.

Meta separation–fusion for generalizable person re-identification

Domain generalization (DG) person re-identification (Re-ID) with a good generalization ability on unseen domains has received widespread attention. Existing DG person Re-ID methods usually adopt some multi-source domain training strategies to improve the generalization ability of their models. However, the style of unseen domains usually changes with application scenarios, which requires DG person Re-ID models to be able to adapt to variable real-world application scenarios. In view of this, we propose a meta separation–fusion network (MSF-Net) for DG Re-ID based on a multi-source domain training strategy and a meta-learning framework. Specifically, we first design a feature separation module to separate the identity-related and background features of samples. Then, we design a feature fusion module to diversify the features of meta-test samples. Through the feature separation and fusion, we can obtain meta-test sample features that contain multiple image styles. More importantly, the feature separation and fusion cooperate with each other to achieve a meta separation–fusion strategy, by which our model can learn more image styles using a limited number of samples in source domains and thus has a stronger generalization ability on unseen domains. Extensive experimental results show that our MSF-Net has reliable performance.

Pose-Aided Video-Based Person Re-Identification via Recurrent Graph Convolutional Network

Existing methods for video-based person re-identification (ReID) mainly learn the appearance feature of a given pedestrian via a feature extractor and a feature aggregator. However, the appearance models would fail to learn a large inter-class variance when different pedestrians have similar appearances. Considering that different pedestrians have different walking postures and body proportions, we propose to learn the discriminative pose feature beyond the appearance feature for video retrieval. Specifically, we implement a two-branch architecture to separately learn the appearance feature and pose feature, and then concatenate them together for inference. To learn the pose feature, we first detect the pedestrian pose in each frame through an off-the-shelf pose detector, and construct a temporal graph using the pose sequence. We then exploit a recurrent graph convolutional network (RGCN) to learn the node embeddings of the temporal pose graph, which devises a global information propagation mechanism to simultaneously achieve the neighborhood aggregation of intra-frame nodes and message passing among inter-frame graphs. Finally, we propose a dual-attention method (DAM) consisting of node-attention and time-attention to obtain the temporal graph representation from the node embeddings, where the self-attention mechanism is employed to learn the importance of each node and each frame. We verify the proposed method on three video-based ReID datasets, i.e., Mars, DukeMTMC and iLIDS-VID, whose experimental results demonstrate that the learned pose feature can effectively improve the performance of existing appearance models.

CCSD: cross-camera self-distillation for unsupervised person re-identification

Existing unsupervised person re-identification (Re-ID) methods have achieved remarkable performance by adopting an alternate clustering-training manner. However, they still suffer from camera variation, which results in an inconsistent feature space and unreliable pseudo labels that severely degrade the performance. In this paper, we propose a cross-camera self-distillation (CCSD) framework for unsupervised person Re-ID to alleviate the effect of camera variation. Specifically, in the clustering phase, we propose a camera-aware cluster refinement mechanism, which first splits each cluster into multiple clusters according to the camera views, and then refines them into more compact clusters. In the training phase, we first obtain the similarity between the samples and the refined clusters from the same and different cameras, and then transfer the knowledge of similarity distribution from intra-camera to cross-camera. Since the intra-camera similarity is free from camera variation, our knowledge distillation approach is able to learn a more consistent feature space across cameras. Extensive experiments demonstrate the superiority of our proposed CCSD against the state-of-the-art approaches on unsupervised person Re-ID.