Unsupervised Person Re-Identification via Multi-Label Classification

By Dongkai Wang, Shiliang Zhang. Computer Vision and Pattern Recognition, 2020

416 citations recorded by the source corpus.

The challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels. Our method starts by assigning each person image with a single-class label, then evolves to multi-label classification by leveraging the updated ReID model for label prediction. The label prediction comprises similarity computation and cycle consistency to ensure the quality of predicted labels. To boost the ReID model training efficiency in multi-label classification, we further propose the memory-based multi-label classification loss (MMCL). MMCL works with memory-based non-parametric classifier and integrates multi-label classification and single-label classification in an unified framework. Our label prediction and MMCL work iteratively and substantially boost the ReID performance. Experiments on several large-scale person ReID datasets demonstrate the superiority of our method in unsupervised person ReID. Our method also allows to use labeled person images in other domains. Under this transfer learning setting, our method also achieves state-of-the-art performance.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4dcbb68106dee0b5f68f6060c836b40cd7c053c3

How researchers see this paper

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

In Computer Vision and Pattern Recognition

  1. Weihao Yuan
  2. Guangyuan Wang
  3. Erwin M. Bakker
  4. Ping Tan
  5. Zuozhuo Dai
  6. Michael S. Lew
  7. Wei Chen
  8. Siyu Zhu

Citations in the corpus