Fully Unsupervised Person Re-Identification via Selective Contrastive Learning

Unsupervised person re-identification (Re-ID) has better scalability and practicability than supervised Re-ID in the actual deployment. However, it is difficult to learn a discriminative Re-ID model without annotations. To address the above issue, we propose an end-to-end Self-supervised Agent Learning (SAL) algorithm by exploiting a set of agents as a bridge to reduce domain gaps for unsupervised cross-domain person Re- ID. The proposed SAL model enjoys several merits. First, to the best of our knowledge, this is the first work to exploit selfsupervised learning for unsupervised person Re-ID. Second, our model has designed three effective learning mechanisms including supervised label learning in source domain, similarity consistency learning in target domain, and self-supervised learning in cross domain, which can learn domain-invariant yet discriminative representations through the principled lens of agent learning by reducing domain discrepancy adaptively. Extensive experimental results on three standard benchmarks demonstrate that the proposed SAL performs favorably against state-of-the-art unsupervised person Re-ID methods.

Unsupervised domain adaptation (UDA) aims to mitigate the domain shift that occurs when transferring knowledge from a labeled source domain to an unlabeled target domain. While it has been studied for application in unsupervised person re-identification (ReID), the relations of feature distribution across the source and target domains remain underexplored, as they either ignore the local relations or omit the in-depth consideration of negative transfer when two domains do not share identical label spaces. In light of the above, this paper presents an innovative part-aware progressive adaptation network (PPAN) that exploits global and local relations for UDA-based ReID across domains. A multi-branch network is developed that explicitly learns discriminative feature representation from both whole-body images and body-part images under the supervision of a labeled source domain. Within each network branch, an independent UDA constraint is designed that aligns the global and local feature distributions from a labeled source domain with those of an unlabeled target domain. In addition, a novel progressive adaptation strategy (PAS) is designed that effectively alleviates the negative influence of outlier source identities. The proposed unsupervised ReID model is evaluated on five widely used datasets (Market-1501, DukeMTMC-reID, CUHK03, VIPeR and PRID), and experimental results demonstrate its superior robustness and effectiveness relative to state-of-the-art approaches.

The challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels. Our method starts by assigning each person image with a single-class label, then evolves to multi-label classification by leveraging the updated ReID model for label prediction. The label prediction comprises similarity computation and cycle consistency to ensure the quality of predicted labels. To boost the ReID model training efficiency in multi-label classification, we further propose the memory-based multi-label classification loss (MMCL). MMCL works with memory-based non-parametric classifier and integrates multi-label classification and single-label classification in a unified framework. Our label prediction and MMCL work iteratively and substantially boost the ReID performance. Experiments on several large-scale person ReID datasets demonstrate the superiority of our method in unsupervised person ReID. Our method also allows to use labeled person images in other domains. Under this transfer learning setting, our method also achieves state-of-the-art performance.

Currently, the mainstream unsupervised method uses a clustering algorithm to cluster unlabeled data and generate labels for training samples based on the clustering results. The critical step is to obtain the features. Most unsupervised methods are based on single-branch networks. Still, multi-branch networks that fusion local and global features have been proved to improve supervised effectively. This paper studies the problem of unsupervised person re-identification using the multi-branch network. The goal is to extract more reliable feature representation through the multi-branch network and obtain a model with a more vital distinguishing ability. Specifically, an OSNet-based multi-branch network simultaneously extracts global, local, and channel features. It applies a bottom-up clustering algorithm based on the hierarchy to create labels for unlabeled training samples and uses Softmax-Triplet joint loss to optimize the model. We verify the proposed method on two benchmark re-ID datasets, such as the Market-1501 and DukeMTMC-reID datasets. Compared with the baseline method, the accuracy of Rank-1 and mAP are improved by 5.5 and 12.6% on Market-1501, and 5.5 and 7.6% on DukeMTMC-reID.

Unsupervised person reidentification (Re-ID) is crucial since it enables the matching of individuals without labeled data. Existing clustering-based methods directly discard outlier samples. However, these discarded outliers are not noise samples. In contrast, they are some high-quality samples that are especially meaningful for implementing Re-ID cross-camera retrieval. To capitalize on the diversity of data, we propose a pose-aligned outlier sample relabeling (POSR) model to relabel these outliers to mine diverse data representations for accurate cross-camera retrieval. POSR consists of a pose-aligned feature learning (PFL) module and a biclustering outlier relabeling (BOR) module. The PFL module learns pose features with fine-grained information about human joint points by dynamically matching tokens and obtains the pose-aligned feature via average pooling. The pose-aligned features can compensate for the limitations of global features obtained through the transformer encoder for alignment processing. Therefore, the BOR module is proposed to relabel outlier samples through the complementarity of pose-aligned features and global features, which can learn ID-consistent representations and achieve more robust performance for cross-camera retrieval of unsupervised Re-ID by training meaningful outlier samples. Extensive experiments on three datasets demonstrate the effectiveness of our method and significantly improve Re-ID accuracy.

Unsupervised person reidentification (re-ID) is designed to deal with the problem that in industrial application scenarios, the consistent features of the same person cannot be fully mined due to the lack of annotated information in the collected image resources. Researchers focus on using pseudolabels to label images with the same clustering attributes, but traditional clustering methods are prone to generating noisy pseudolabels, which greatly reduce the accuracy of unsupervised person re-ID. We propose a method to refine pseudolabels by generating discriminative information based on channel partitioning. In the design process, the feature map is divided from the channel level, generating a proximity matrix by calculating the distance between the channel feature and the global feature, and select the most negative sample as the verification label to optimize the pseudolabel of the global feature. As a bidirectional guide, the global pseudolabel can be used to further smooth each channel label, keeping the consistency of channel features and global features in pseudolabel selection. This unique method of learning local features can link global information and channel information. Experimental results demonstrate the superior performance of our proposal on representative person re-ID datasets.

As supervised person re-identification (Re-Id) requires massive labeled pedestrian data and it is very difficult to collect sufficient labeled data in reality, unsupervised Re-Id approaches attract much more attention than the former. Existing unsupervised person Re-Id models learn global features of pedestrian from whole images or several constant patches. These models ignore the difference of each region in the whole pedestrian images for feature representation, such as occluded and pose invariant regions, and thus reduce the robustness of models for cross-view feature learning. To solve these issues, we propose an Unsupervised Region Attention Network (URAN) that can learn the cross-view region attention features from the cropped pedestrian images, fixed by region importance weights on images. The proposed URAN designs a Pedestrian Region Biased Enhance (PRBE) loss to produce high attention weights for most important regions in pedestrian images. Furthermore, the URAN employs a first neighbor relation grouping algorithm and a First Neighbor Relation Constraint (FNRC) loss to provide the training direction of the unsupervised region attention network, such that the region attention features are discriminant enough for unsupervised person Re-Id task. In experiments, we consider two popular datasets, Market1501 and DukeMTMC-reID, as evaluation of PRBE and FNRC loss, and their balance parameter to demonstrate the effectiveness and efficiency of the proposed URAN, and the experimental results show that the URAN provides better performance than the-state-of-the-arts (higher than existing methods at least 1.1%).

Instance-aware diversity feature generation 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.

Traditional person re-identification methods are mostly based on supervised state of manually annotated data sets. Although the recognition accuracy is high, the algorithm completely relies on effective annotation information and lacks practicability. Based on the above problems, an unsupervised person re-identification method is proposed, which refines features to guide multi-label distribution sorting learning. Firstly, a single and multi-label classification network structure is constructed to improve the matching accuracy of tags by learning the characteristics of each person and its k nearest neighbor and sharing the same class. Secondly, the refinement feature extraction module is designed and embedded into the original ResNet50 network, and the potential key areas in the person image are adaptively located. While weakening the appearance differences of the features, multi-information mining is carried out to obtain the refined features of the characters and assist the classification network to improve the performance. Thirdly, reliable multi-category labels are screened by punishing the sorting between positive and negative categories of labels in multi-category labels. Finally, the network is supervised by combining multi-label distribution sorting loss and multi-label classification loss. Experiments show that without any annotation information, the recognition accuracy of Market-1501 and DukeMTMC-reID datasets is 58.4% and 42.3%, respectively, and the mAP of Market-1501 dataset is increased by 12.9%.

Unsupervised person re-identification (re-ID) aims to perform person retrieval in an unsupervised manner across multiple cameras. Most recent works usually adopted contrastive learning with clustering strategy to guide learning process. However, the domain gap between cameras easily causes the high intra-class variance and prohibits an effective contrastive learning. To overcome this problem, we propose dual-graph contrastive learning (Dual-GCL) to fully utilize the structures between the instances as well as the relationship between the instances and the centroids generated by the clustering strategy. Firstly, a dual-graph is constructed by utilizing the affinities of instances in the feature space and the pseudo-label space derived from clustering strategy with the node-to-node contrastive learning. Then, to capture the relations between the dual-graph and the centroids, we perform dual-graph contrastive learning at both the node level and the super-node level. The contrastive learning based on the two levels can encode multi-level structural representations between the instances corresponding to the nodes in dual-graph and align the centroids between different cameras in the shared embedding space. Moreover, a camera-aware augmentation scheme that exploits the semantic relationship is proposed to alleviate the domain discrepancy between cameras. Experimental results demonstrate that our approach outperforms the state-of-the-art methods.

Unsupervised person re-identification (ReID) has recently gained significant attention from researchers. ReID matches images of the same person from different camera views in various scenes without any labels. Existing clustering methods primarily rely on a fixed threshold (the maximum distance between sample points and clustering centroids) and overlook the importance of adjusting this threshold during continuous model optimization. This mismatch between clustering thresholds and inter- or intra-class spacing reduces clustering accuracy. To address this issue, this study proposes an Adaptive Clustering and Weighted Regularization Contrastive Learning (ACWRCL) framework for unsupervised person ReID. The ACWRCL framework comprises two main components: (1) the Clustering Threshold Adaptive Adjustment (CTAA) module, and (2) the Weighted Regularization Contrastive Learning (WRCL) module. The CTAA module dynamically adjusts the clustering threshold to align with model optimization, ensuring that the threshold remains within an appropriate range to prevent under- or over-robustness in the clustering model. The WRCL module uses the similarity ratio between the query sample and the clustering centroid relative to the overall similarity of all samples with the same labels as the query sample. This ratio is used as the weight in the loss function to penalize incorrect clustering and improve pseudo-label generation accuracy. Extensive experiments on public ReID datasets—Market-1501, MSMT17, Veri776, CUHK03, and PersonX—demonstrate the effectiveness of the proposed method.

Debiased hybrid contrastive learning with hard negative mining 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.

Existing unsupervised Re-ID methods often rely on pseudo-labels generated by clustering algorithms. However, the effectiveness of these methods is highly dependent on the quality of the learned features. As a result, improving the quality of the extracted features will highly enhance the performance of the model. In this paper, an attention-based hybrid contrastive learning method (AHCL) is proposed by incorporating a novel attention mechanism, which combines spatial attention and channel attention to enable the model to learn more effective features. Additionally, a hybrid contrastive learning approach is introduced, which utilizes a memory dictionary to store features and extracts both cluster-level and instance-level features for contrastive learning. For cluster-level contrastive loss, it ensures that the network is updated in a more stable way by comparing the sample with the cluster center. Meanwhile, it can extract more discriminative information by comparing the sample with hard samples in instance-level contrastive loss. Thus, the performance of the model would be improved by using the combination of this two loss. The experimental results on three widely-used large-scale Re-ID datasets and experimental settings demonstrate that the proposed AHCL outperforms the compared existing methods and significantly enhances the accuracy of unsupervised person Re-identification.