Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer
This addresses the problem of identifying occluded persons in crowded scenes for surveillance and security applications, presenting a novel method but with incremental improvements over existing approaches.
The paper tackles occluded person re-identification by proposing a Part-Aware Transformer (PAT) that discovers diverse parts in a weakly supervised manner, achieving favorable performance against state-of-the-art methods on six benchmarks for occluded, partial, and holistic Re-ID tasks.
Occluded person re-identification (Re-ID) is a challenging task as persons are frequently occluded by various obstacles or other persons, especially in the crowd scenario. To address these issues, we propose a novel end-to-end Part-Aware Transformer (PAT) for occluded person Re-ID through diverse part discovery via a transformer encoderdecoder architecture, including a pixel context based transformer encoder and a part prototype based transformer decoder. The proposed PAT model enjoys several merits. First, to the best of our knowledge, this is the first work to exploit the transformer encoder-decoder architecture for occluded person Re-ID in a unified deep model. Second, to learn part prototypes well with only identity labels, we design two effective mechanisms including part diversity and part discriminability. Consequently, we can achieve diverse part discovery for occluded person Re-ID in a weakly supervised manner. Extensive experimental results on six challenging benchmarks for three tasks (occluded, partial and holistic Re-ID) demonstrate that our proposed PAT performs favorably against stat-of-the-art methods.