English

Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification

Computer Vision and Pattern Recognition 2020-11-04 v1

Abstract

Recent advances in person re-identification have demonstrated enhanced discriminability, especially with supervised learning or transfer learning. However, since the data requirements---including the degree of data curations---are becoming increasingly complex and laborious, there is a critical need for unsupervised methods that are robust to large intra-class variations, such as changes in perspective, illumination, articulated motion, resolution, etc. Therefore, we propose an unsupervised framework for person re-identification which is trained in an end-to-end manner without any pre-training. Our proposed framework leverages a new attention mechanism that combines group convolutions to (1) enhance spatial attention at multiple scales and (2) reduce the number of trainable parameters by 59.6%. Additionally, our framework jointly optimizes the network with agglomerative clustering and instance learning to tackle hard samples. We perform extensive analysis using the Market1501 and DukeMTMC-reID datasets to demonstrate that our method consistently outperforms the state-of-the-art methods (with and without pre-trained weights).

Keywords

Cite

@article{arxiv.2011.01888,
  title  = {Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification},
  author = {Kshitij Nikhal and Benjamin S. Riggan},
  journal= {arXiv preprint arXiv:2011.01888},
  year   = {2020}
}

Comments

WACV 2021

R2 v1 2026-06-23T19:53:36.947Z