Kim, Minsu Kim, Seungryong Park, Jungin Park, Seongheon Sohn, Kwanghoon 2024-01-12T02:45:53Z 2024-01-12T02:45:53Z 2023-11-30 2023-06 1063-6919 https://pubs.kist.re.kr/handle/201004/76423 Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based Visible-Infrared person Re-IDentification (VI-ReID) models remains unexplored. In this paper, we present a novel data augmentation technique, dubbed PartMix, that synthesizes the augmented samples by mixing the part descriptors across the modalities to improve the performance of part-based VI-ReID models. Especially, we synthesize the positive and negative samples within the same and across different identities and regularize the backbone model through contrastive learning. In addition, we also present an entropy-based mining strategy to weaken the adverse impact of unreliable positive and negative samples. When incorporated into existing part-based VI-ReID model, PartMix consistently boosts the performance. We conduct experiments to demonstrate the effectiveness of our PartMix over the existing VI-ReID methods and provide ablation studies. English IEEE COMPUTER SOC PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification Conference 10.1109/CVPR52729.2023.01786 1 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.18621 - 18632 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 18621 18632 US Vancouver, CANADA 2023-06-17 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) 001062531302090 2-s2.0-85168140921