Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification

arXiv:2405.05613v1 Announce Type: new
Abstract: Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities without any annotations. Recently, clustered pseudo-label methods have become predominant in USVI-ReID, although the inherent noise in pseudo-labels presents a significant obstacle. Most existing works primarily focus on shielding the model from the harmful effects of noise, neglecting to calibrate noisy pseudo-labels usually associated with hard samples, which will compromise the robustness of the model. …

abstract annotations arxiv become challenge cs.cv identification images labels match noise pedestrian person robust type unsupervised