Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification

arXiv:2403.10782v1 Announce Type: new
Abstract: A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single intermediate bridging domain are often less effective, as this generated domain may not adequately capture sufficient common discriminant information. This paper introduces the Bidirectional Multi-step Domain Generalization (BMDG), a novel approach for unifying feature representations across diverse modalities. BMDG creates multiple virtual intermediate domains by finding …

abstract art arxiv challenge cs.cv domain generate generated identification intermediate key person state training type