RGB-Infrared person re-identification (RGB-IR ReID) aims to associate people across disjoint RGB and IR camera views. Currently, state-of-the-art performance of RGB-IR ReID is not as impressive that conventional ReID. Much due the notorious modality bias training issue brought by single-modality ImageNet pre-training, which might yield RGB-biased representations severely hinder cross-modality i...

Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation. A potential limitation of these clustering-based methods is that they always tend introduce noisy labels, which will undoubtedly hamper the performance our re-ID system. To handle this limitation, an intuitive solution utiliz...