Recently some researches have focused on the Domain-Generalization (DG) Re-ID problem that training and testing are not in the same domain distribution. To fit the unseen complex scenes, recently deep feature matching-based methods for DG Re-ID have been developed and achieved the state-of-the-arts. However, they ignored some cases in which the accuracy of key region matching is unstable at a single scale, and the bad impact of style variations for feature representations. To address the issues, we propose a novel deep image matching model named Multi-scale Transformer-based Matching Network (MTMN) for DG Re-ID problem. MTMN matches two images with multi-scale local respondence instead of fixed representations. Specifically, the Transformer is carefully modified to formulate efficient local interactions between query and gallery images in multiple scales. Moreover, the style normalization is introduced to filter out identity-irrelated features to promote the matching results. Comprehensive experiments on several DG Re-ID tasks demonstrate the superiority of the proposed method compared with the state-of-the-arts, e.g., 5.4% and 2.6% gains in Rank-1 and mAP on Market-1501 $\rightarrow$ MSMT17(V1) task.

With the increasing demand for person re-identification (Re-ID) tasks, the need for all-day retrieval has become an inevitable trend. Nevertheless, single-modal Re-ID is no longer sufficient to meet this requirement, making Multi-Modal Data crucial in Re-ID. Consequently, a Visible-Infrared Person Re-Identification (VI Re-ID) task is proposed, which aims to match pairs of person images from the visible and infrared modalities. The significant modality discrepancy between the modalities poses a major challenge. Existing VI Re-ID methods focus on cross-modal feature learning and modal transformation to alleviate the discrepancy but overlook the impact of person contour information. Contours exhibit modality invariance, which is vital for learning effective identity representations and cross-modal matching. In addition, due to the low intra-modal diversity in the visible modality, it is difficult to distinguish the boundaries between some hard samples. To address these issues, we propose the Graph Sampling-based Multi-stream Enhancement Network (GSMEN). Firstly, the Contour Expansion Module (CEM) incorporates the contour information of a person into the original samples, further reducing the modality discrepancy and leading to improved matching stability between image pairs of different modalities. Additionally, to better distinguish cross-modal hard sample pairs during the training process, an innovative Cross-modality Graph Sampler (CGS) is designed for sample selection before training. The CGS calculates the feature distance between samples from different modalities and groups similar samples into the same batch during the training process, effectively exploring the boundary relationships between hard classes in the cross-modal setting. Some experiments conducted on the SYSU-MM01 and RegDB datasets demonstrate the superiority of our proposed method. Specifically, in the VIS→IR task, the experimental results on the RegDB dataset achieve 93.69% for Rank-1 and 92.56% for mAP.

While person re-identification (Re-ID) task has made significant progress in closed-set setting in recent years, its generalizability to unknown domains continues to be limited. To tackle the issue, domain generalization (DG) Re-ID task has been proposed. Current state-of-the-art approach involves deep feature matching, where key regions of image pairs are matched at same scale. However, the method does not take into account variability of angles in real image acquisition. In order to resolve the problem, we propose an innovative deep image matching framework called Cross-scale Transformer-based Matching Network (CTMN) for DG Re-ID task. CTMN model matches two images through cross-scale local respondence rather than using fixed representations. The Transformer is specifically adjusted to enable effective local interactions between query and gallery images across different scales. Additionally, deformable convolution is incorporated to better segment local regions of person before procedure for matching image pairs. Lastly, Style Normalization Module (SNM) is added to remove identity-irrelevant features, improving the matching results. Extensive experiments on multiple DG Re-ID tasks demonstrate the advantages of our proposed method over existing state-of-the-arts.