Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer

By Yulin Li, Jianfeng He, Tianzhu Zhang, Xiang Liu, Yongdong Zhang, Feng Wu. 2021

401 citations recorded by the source corpus.

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 encoder-decoder 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 favor-ably against stat-of-the-art methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yaping Huang
  2. Haibin Ling
  3. Qingji Guan

In Computer Vision and Pattern Recognition

  1. Yaping Huang
  2. Haibin Ling
  3. Yuming Liu
  4. Qingji Guan
  5. Mengyang Pu
  6. Ming-Hsuan Yang
  7. Luc Van Gool
  8. Huchuan Lu

In Model Architectures

  1. Yaping Huang
  2. Haibin Ling
  3. Qingji Guan

Citations in the corpus