Feature Completion Transformer for Occluded Person Re-identification

arXiv:2303.01656v2 Announce Type: replace
Abstract: Occluded person re-identification (Re-ID) is a challenging problem due to the destruction of occluders. Most existing methods focus on visible human body parts through some prior information. However, when complementary occlusions occur, features in occluded regions can interfere with matching, which affects performance severely. In this paper, different from most previous works that discard the occluded region, we propose a Feature Completion Transformer (FCFormer) to implicitly complement the semantic information of occluded parts in the …

abstract arxiv cs.cv destruction feature features focus however human identification information paper performance person prior through transformer type