Unsupervised Person Re-identification Research Articles

Multi-view similarity aggregation and multi-level gap optimization for unsupervised person re-identification

Currently, unsupervised person re-identification (Re-ID) typically directly computes the similarity matrix between samples and then applies clustering algorithms to generate pseudo labels for model training, achieving significant progress to some extent. However, distance matrices calculated from a single perspective cannot effectively handle complex and variable sample noise environments, leading to pseudo labels that are not comprehensive or accurate enough, with considerable noise that can misguide model optimization. To address this issue, this paper proposes a Multi-view Similarity Aggregation and Multi-level Gap Optimization (MSAMGO) to improve the accuracy of pseudo labels before and after clustering. Specifically, Multi-view Similarity Aggregation (MSA) involves integrating similarity matrices calculated from multiple perspectives to generate reliable pseudo labels for clustering, greatly reducing noise interference from the source. Additionally, the Multi-level Gap Optimization (MGO) is introduced to leverage the positive and negative centroids of similarity between cluster-level samples and the correlation between instance-level samples. Together, they ensure the overall quality of pseudo-labels, reduce noise interference, and collectively promote model optimization. Experiments were conducted on several datasets, demonstrating that our method surpasses the majority of existing unsupervised person re-identification to a large extent and exhibits excellent generalization.

Distilling consistent relations for multi-source domain adaptive person re-identification

Although unsupervised person re-identification has made great progress by employing domain adaptation, existing methods rarely make use of multiple source datasets. These works neglect a practical scenario where annotated data from multiple domains are available. To address this issue, we propose a novel method to exploit the diversity and consistency of multiple sources to improve domain adaptation for person re-identification. In the proposed method, multiple expert models pre-trained in different source domains are adapted to the target domain by self-training with expert-specific clustering-based pseudo labels. To improve the consistency of multiple experts, we transfer knowledge between experts through dual similarity distillation between experts. Finally, to further encourage experts to learn complementary features, we maintain the feature diversity of multiple experts by representation decorrelation, preventing them from being too similar. Extensive experiments conducted on three benchmarks, Market-1501, DukeMTMC-reID, and MSMT17, demonstrate the effectiveness of the proposed method.

DCSG: data complement pseudo-label refinement and self-guided pre-training for unsupervised person re-identification

DCSG: data complement pseudo-label refinement and self-guided pre-training for unsupervised person re-identification

Clothing-invariant contrastive learning for unsupervised person re-identification

Clothing change person re-identification (CC-ReID) aims to match images of the same person wearing different clothes across diverse scenes. Leveraging biological features or clothing labels, existing CC-ReID methods have demonstrated promising performance. However, current research primarily focuses on supervised CC-ReID methods, which require a substantial number of manually annotated labels. To tackle this challenge, we propose a novel clothing-invariant contrastive learning (CICL) framework for unsupervised CC-ReID task. Firstly, to obtain clothing change positive pairs at a low computational cost, we propose a random clothing augmentation (RCA) method. RCA initially partitions clothing regions based on parsing images, then applies random augmentation to different clothing regions, ultimately generating clothing change positive pairs to facilitate clothing-invariant learning. Secondly, to generate pseudo-labels strongly correlated with identity in an unsupervised manner, we design semantic fusion clustering (SFC), which enhances identity-related information through semantic fusion. Additionally, we develop a semantic alignment contrastive loss (SAC loss) to encourages the model to learn features strongly correlated with identity and enhances the model’s robustness to clothing changes. Unlike existing optimization methods that forcibly bring closer clusters with different pseudo-labels, SAC loss aligns the clustering results of real image features with those generated by SFC, forming a mutually reinforcing scheme with SFC. Experimental results on multiple CC-ReID datasets demonstrate that the proposed CICL not only outperforms existing unsupervised methods but can even achieves competitive performance with supervised CC-ReID methods. Code is made available at https://github.com/zqpang/CICL.

Inter-camera Identity Discrimination for Unsupervised Person Re-identification

Unsupervised person re-identification (Re-ID) has garnered significant attention because of its data-friendly nature, as it does not require labeled data. Existing approaches primarily address this challenge by employing feature-clustering techniques to generate pseudo-labels. In addition, camera-proxy-based methods have emerged because of their impressive ability to cluster sample identities. However, these methods often blur the distinctions between individuals within inter-camera views, which is crucial for effective person re-ID. To address this issue, this study introduces an inter-camera-identity-difference-based contrastive learning framework for unsupervised person Re-ID. The proposed framework comprises two key components: (1) a different sample cross-view close-range penalty module and (2) the same sample cross-view long-range constraint module. The former aims at penalizing excessive similarity among different subjects across inter-camera views, whereas the latter mitigates the challenge of excessive dissimilarity among the same subject across camera views. To validate the performance of our method, we conducted extensive experiments on three existing person Re-ID datasets (Market-1501, MSMT17, and PersonX). The results demonstrate the effectiveness of the proposed method, which shows a promising performance. The code is available at https://github.com/hooldylan/IIDCL .

Learning the Meta Feature Transformer for Unsupervised Person Re-Identification

Although unsupervised person re-identification (Re-ID) has drawn increasing research attention, it still faces the challenge of learning discriminative features in the absence of pairwise labels across disjoint camera views. To tackle the issue of label scarcity, researchers have delved into clustering and multilabel learning using memory dictionaries. Although effective in improving unsupervised Re-ID performance, these methods require substantial computational resources and introduce additional training complexity. To address this issue, we propose a conceptually simple yet effective and learnable module effective block, named the meta feature transformer (MFT). MFT is a streamlined, lightweight network architecture that operates without the need for complex networks or feature memory bank storage. It primarily focuses on learning interactions between sample features within small groups using a transformer mechanism in each mini-batch. It then generates a new sample feature for each group through a weighted sum. The main benefits of MFT arise from two aspects: (1) it allows for the use of numerous new samples for training, which significantly expands the feature space and enhances the network’s generalization capabilities; (2) the trainable attention weights highlight the importance of samples, enabling the network to focus on more useful or distinguishable samples. We validate our method on two popular large-scale Re-ID benchmarks, where extensive evaluations show that our MFT outperforms previous methods and significantly improves Re-ID performances.

Patch-based tendency camera multi-constraint learning for unsupervised person re-identification

Unsupervised person re-identification (ReID) is a task that aims to retrieve pedestrians across different cameras from unlabeled data. Existing methods rely on clustering to generate pseudo-labels, but they are inevitably noisy. Although pseudo-label refinement approaches have been presented, the essentiality of patch contours is ignored. The tendency analysis of retrieval between global and patch features has not been well investigated. In this paper, we propose a Patch-based Tendency Camera Multi-Constraint Learning (PTCML) model for unsupervised person ReID. First, to explore the tendentious retrieval of global and patch features, we design a Ranking Tendency Similarity (RTS) score by gauging the distribution discrepancy of distance changes. Second, based on RTS score, we propose a Tendency-based Mutual Complementation (TMC) loss to improve the quality of global and patch pseudo-labels. Third, to resist camera variations, we propose an Adaptive Camera Multi-Constraint (ACM) loss to optimize recognition results with camera distribution constraint and instance constraint simultaneously. Finally, numerous experiments on Market-1501 and MSMT17 demonstrate that our method can significantly surpass the state-of-the-art performance.

Joint training with local soft attention and dual cross-neighbor label smoothing for unsupervised person re-identification

AbstractExisting unsupervised person re-identification approaches fail to fully capture the fine-grained features of local regions, which can result in people with similar appearances and different identities being assigned the same label after clustering. The identity-independent information contained in different local regions leads to different levels of local noise. To address these challenges, joint training with local soft attention and dual cross-neighbor label smoothing (DCLS) is proposed in this study. First, the joint training is divided into global and local parts, whereby a soft attention mechanism is proposed for the local branch to accurately capture the subtle differences in local regions, which improves the ability of the re-identification model in identifying a person’s local significant features. Second, DCLS is designed to progressively mitigate label noise in different local regions. The DCLS uses global and local similarity metrics to semantically align the global and local regions of the person and further determines the proximity association between local regions through the cross information of neighboring regions, thereby achieving label smoothing of the global and local regions throughout the training process. In extensive experiments, the proposed method outperformed existing methods under unsupervised settings on several standard person re-identification datasets.

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.

Joint global feature and part-based pyramid features for unsupervised person re-identification

Joint global feature and part-based pyramid features for unsupervised person re-identification

Progressive spatial–temporal transfer model for unsupervised person re-identification

Progressive spatial–temporal transfer model for unsupervised person re-identification

Loose–tight cluster regularization for unsupervised person re-identification

Loose–tight cluster regularization for unsupervised person re-identification

Multi-Grained feature aggregation based on Transformer for unsupervised person re-identification

Multi-Grained feature aggregation based on Transformer for unsupervised person re-identification

Intra-Inter Domain Similarity for Unsupervised Person Re-Identification.

Most of unsupervised person Re-Identification (ReID) works produce pseudo-labels by measuring the feature similarity without considering the domain discrepancy among cameras, leading to degraded accuracy in pseudo-label computation across cameras. This paper targets to address this challenge by decomposing the similarity computation into two stages, i.e., the intra-domain and inter-domain computations, respectively. The intra-domain similarity directly leverages CNN features learned within each camera, hence generates pseudo-labels on different cameras to train the ReID model in a multi-branch network. The inter-domain similarity considers the classification scores of each sample on different cameras as a new feature vector. This new feature effectively alleviates the domain discrepancy among cameras and generates more reliable pseudo-labels. We further propose the Instance and Camera Style Normalization (ICSN) to enhance the robustness to domain discrepancy. ICSN alleviates the intra-camera variations by adaptively learning a combination of instance and batch normalization. ICSN also boosts the robustness to inter-camera variations through TNorm which converts the original style of features into target styles. The proposed method achieves competitive performance on multiple datasets under fully unsupervised, intra-camera supervised and domain generalization settings, e.g., it achieves rank-1 accuracy of 64.4% on the MSMT17 dataset, outperforming the recent unsupervised methods by 20+%.

Diverse semantic information fusion for Unsupervised Person Re-Identification

Unsupervised Person Re-Identification (Re-ID) has achieved considerable success through leveraging various approaches that rely on hard pseudo-labels. Prior work mainly focused on improving the quality of pseudo-labels or enhancing the robustness of representation learning model. However, there has been little focus on exploring the contextual semantic information, which can reveal rich relations within samples and provide complementary knowledge to assist the hard pseudo-labels. To this end, we propose a novel method named FuseDSI to explore the potential to harness diverse contextual semantic information fusion. In addition to the hard pseudo labels, FuseDSI explores additional pair-wise semantic information and neighborhood semantic information within each mini-batch through online self-exploration. Furthermore, it leverages the explored semantic information as an additional supervisory signal to enhance robust representation learning. For these two types of contextual semantic information are dynamically estimated in an online manner based on the model’s status, they complement each other well with the hard pseudo-labels. One significant advantage of FuseDSI is its flexibility in combining various pseudo-labels-based methods. Moreover, since exploring the contextual semantic information requires no external elaborate module nor memory-consuming memory bank, it maintains the structure of baseline model with negligible impact on training time. Experimental studies on two widely used person ReID benchmark datasets (MSMT17, Market-1501) demonstrate that FuseDSI consistently improves the performance of baseline model and achieves the state-of-the-art results. Code is available at: FuseDSI.

Adapt only once: Fast unsupervised person re-identification via relevance-aware guidance

Unsupervised domain adaptive person re-identification (UDA person reID) defines a task where labels in target domains are totally unknown while source domains are fully labeled. Assigning reliable labels quickly is a critical issue for UDA person reID that could be applied in the real-world scenarios. Recent studies focus on obtaining pseudo labels by clustering algorithms and then training the reID model with these labels. However, the main limitation of these methods is the high time complexity, which is caused by the calculation of all pair-wise similarities and multiple iterations in the clustering algorithm to obtain reliable results. When the data is very large or the feature dimensions are very high, the memory and time cost requirements of the clustering algorithm can increase rapidly.In this paper, we provide a fast unsupervised domain adaptive person reID framework (FUReID), which calculates the relevance between unlabeled samples only once to adapt to the new scenarios without any iterations in the stage of label generation. Especially, instead of pursuing accurate labels, FUReID considers constructing a lightweight paradigm to generate coarse labels and then refine these labels during the training stage. Therefore, FUReID designs a prototype-guided labeling method that only relies on calculating the relevance between the prototype vectors and the samples, and assigning coarse labels with noise. Then, to alleviate the issue of noise, FUReID designs a label-flexible training network with an adaptive selection strategy to refine those coarse labels progressively. For several widely-used person reID datasets, our method achieves 81.7%, 26.2%, and 87.7% in mAP on Market1501, MSMT17 and PersonX, respectively. Code is available at https://github.com/AILab90/FUReID.

Spatial and Temporal Dual-Attention for Unsupervised Person Re-Identification

Spatial and Temporal Dual-Attention for Unsupervised Person Re-Identification

Unsupervised Joint Contrastive Learning for Aerial Person Re-Identification and Remote Sensing Image Classification

Unsupervised person re-identification (Re-ID) aims to match the query image of a person with images in the gallery without the use of supervision labels. Most existing methods usually generate pseudo-labels through clustering algorithms for contrastive learning, which inevitably results in noisy labels assigned to samples. In addition, methods that only apply contrastive learning at the clustering level fail to fully consider instance-level relationships between instances. Motivated by this, we propose a joint contrastive learning (JCL) framework for unsupervised person Re-ID. Our proposed method involves creating two memory banks to store features of cluster centroids and instances and applies cluster and instance-level contrastive learning, respectively, to jointly optimize the neural networks. The cluster-level contrastive loss is used to promote feature compactness within the same cluster and reinforce identity similarity. The instance-level contrastive loss is used to distinguish easily confused samples. In addition, we use a WaveBlock attention module (WAM), which can continuously wave feature map blocks and introduce attention mechanisms to produce more robust feature representations of a person without considerable information loss. Furthermore, we enhance the quality of our clustering by leveraging camera label information to eliminate clusters containing single camera captures. Extensive experimental results on two widely used person Re-ID datasets verify the effectiveness of our JCL method. Meanwhile, we also used two remote sensing datasets to demonstrate the generalizability of our method.

UnA-Mix: Rethinking Image Mixtures for Unsupervised Person Re-Identification

With the development of ultra-long-range visual sensors, the application of unsupervised person re-identification algorithms to them has become increasingly important. However, these algorithms inevitably generate noisy pseudo-labels, which seriously hinder the performance of tasks over a large range. Mixup, a data enhancement technique, has been validated in supervised learning for its generalization to noisy labels. Based on this observation, to our knowledge, this study is the first to explore the impact of the mixup technique on unsupervised person re-identification, which is a downstream task of contrastive learning, in detail. Specifically, mixup was applied in different locations (at the pixel level and feature level) in an unsupervised person re-identification framework to explore its influences on task performance. In addition, based on the richness of the information contained in the person samples to be mixed, we propose an uncertainty-aware mixup (UnA-Mix) method, which reduces the over-learning of simple person samples and avoids the information damage that occurs when information-rich person samples are mixed. The experimental results on three benchmark person re-identification datasets demonstrated the applicability of the proposed method, especially on the MSMT17, where it outperformed state-of-the-art methods by 5.2% and 4.8% in terms of the mAP and rank-1, respectively.

Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification.

Unsupervised person re-identification (Re-ID) is challenging due to the lack of ground-truth labels. Most existing methods rely on pseudo labels estimated via iterative clustering and thus are highly susceptible to performance penalties incurred by the inaccurate estimated number of clusters. Alternatively, we utilize the sample pairs with pairwise pseudo labels to guide the feature learning to avoid the dilemma of determining cluster numbers. In this article, we propose a meta pairwise relationship distillation (MPRD) method that incorporates a graph convolutional network (GCN) to provide high-fidelity pairwise relationships to supervise the model training. A small amount of metadata with very-confidence pairwise relationships and the unlabeled pairs with the provided pseudo pairwise relationships participate in the GCN training. Besides, we introduce a hard sample deduction (HSD) module to timely mine the sample pairs with error-prone pairwise pseudo labels to mitigate the misled optimization by noisy labels. Furthermore, since the features of each positive pair represent the same person, we design a positive pair alignment (PPA) module to reduce the redundant information in each feature, which is achieved by minimizing the difference between each positive pair's feature distributions. Extensive experiments on the Market-1501, DukeMTMC-reID, and MSMT17 datasets show that our method outperforms the state-of-the-art unsupervised methods.