Structured Domain Adaptation With Online Relation Regularization for Unsupervised Person Re-ID

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.

BiFPN-enhanced SwinDAT-based cherry variety classification with YOLOv8

Accurate classification of cherry varieties is crucial for their economic value and market differentiation, yet their genetic diversity and visual similarity make manual identification challenging, hindering efficient agricultural and trade practices. This study addresses this issue by proposing a novel deep learning-based hybrid model that integrates BiFPN with the YOLOv8n-cls framework, enhanced by Swin Transformer and Deformable Attention Transformer (DAT) techniques. The model was trained and evaluated on a newly constructed dataset comprising cherry varieties from Turkey's Western Mediterranean region. Experimental results demonstrated the effectiveness of the proposed approach, achieving a precision of 91.91%, recall of 92.0%, F1-score of 91.93%, and an overall accuracy of 91.714%. The findings highlight the model's potential to optimize harvest timing, ensure quality control, and support export classification, thereby contributing to improved agricultural practices and economic outcomes.

Learning to Purification for Unsupervised Person Re-Identification

Unsupervised person re-identification is a challenging and promising task in computer vision. Nowadays unsupervised person re-identification methods have achieved great progress by training with pseudo labels. However, how to purify feature and label noise is less explicitly studied in the unsupervised manner. To purify the feature, we take into account two types of additional features from different local views to enrich the feature representation. The proposed multi-view features are carefully integrated into our cluster contrast learning to leverage more discriminative cues that the global feature easily ignored and biased. To purify the label noise, we propose to take advantage of the knowledge of teacher model in an offline scheme. Specifically, we first train a teacher model from noisy pseudo labels, and then use the teacher model to guide the learning of our student model. In our setting, the student model could converge fast with the supervision of the teacher model thus reduce the interference of noisy labels as the teacher model greatly suffered. After carefully handling the noise and bias in the feature learning, our purification modules are proven to be very effective for unsupervised person re-identification. Extensive experiments on two popular person re-identification datasets demonstrate the superiority of our method. Especially, our approach achieves a state-of-the-art accuracy 85.8% @mAP and 94.5% @Rank-1 on the challenging Market-1501 benchmark with ResNet-50 under the fully unsupervised setting. Code has been available at: https://github.com/tengxiao14/Purification_ReID.

Discriminatively Unsupervised Learning Person Re-Identification via Considering Complicated Images

State-of-the-art purely unsupervised learning person re-ID methods first cluster all the images into multiple clusters and assign each clustered image a pseudo label based on the cluster result. Then, they construct a memory dictionary that stores all the clustered images, and subsequently train the feature extraction network based on this dictionary. All these methods directly discard the unclustered outliers in the clustering process and train the network only based on the clustered images. The unclustered outliers are complicated images containing different clothes and poses, with low resolution, severe occlusion, and so on, which are common in real-world applications. Therefore, models trained only on clustered images will be less robust and unable to handle complicated images. We construct a memory dictionary that considers complicated images consisting of both clustered and unclustered images, and design a corresponding contrastive loss by considering both kinds of images. The experimental results show that our memory dictionary that considers complicated images and contrastive loss can improve the person re-ID performance, which demonstrates the effectiveness of considering unclustered complicated images in unsupervised person re-ID.

Online Unsupervised Domain Adaptation via Reducing Inter- and Intra-Domain Discrepancies

Unsupervised domain adaptation (UDA) transfers knowledge from a labeled source domain to an unlabeled target domain on cross-domain object recognition by reducing a distribution discrepancy between the source and target domains (interdomain discrepancy). Prevailing methods on UDA were presented based on the premise that target data are collected in advance. However, in online scenarios, the target data often arrive in a streamed manner, such as visual image recognition in daily monitoring, which means that there is a distribution discrepancy between incoming target data and collected target data (intradomain discrepancy). Consequently, most existing methods need to re-adapt the incoming data and retrain a new model on online data. This paradigm is difficult to meet the real-time requirements of online tasks. In this study, we propose an online UDA framework via jointly reducing interdomain and intradomain discrepancies on cross-domain object recognition where target data arrive in a streamed manner. Specifically, the proposed framework comprises two phases: classifier training and online recognition phases. In the former, we propose training a classifier on a shared subspace where there is a lower interdomain discrepancy between the two domains. In the latter, a low-rank subspace alignment method is introduced to adapt incoming data to the shared subspace by reducing the intradomain discrepancy. Finally, online recognition results can be obtained by the trained classifier. Extensive experiments on DA benchmarks and real-world datasets are employed to evaluate the performance of the proposed framework in online scenarios. The experimental results show the superiority of the proposed framework in online recognition tasks.