Random gray patch and adaptive graph channel attention for visible-infrared person re-identification

The widespread deployment of video surveillance systems has made person recognition technology essential across various fields, including smart surveillance, law enforcement, and criminal investigation. However, person re-identification (Re-ID) using single-modal images struggles in low-light or nighttime conditions. To address the cross-modal matching challenge between visible and infrared images, we propose a novel method. We introduce a random gray patch (RGP) module that simulates infrared images by converting visible image regions to grayscale, reducing modality discrepancy. Additionally, a non_local adaptive graph channel (NAGC) attention module captures long-range dependencies and adjusts feature channel importance. Finally, we introduce a cross-modal contrast loss, which optimizes feature distances between samples of the same identity across different modalities, further improving cross-modal matching performance. Experimental results on SYSU-MM01 and RegDB datasets show that our method significantly outperforms existing approaches.