Unsupervised Person Re-Identification via Multi-Label Classification
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10978-10987
Abstract
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.Keywords
This publication has 27 references indexed in Scilit:
- Pose-Driven Deep Convolutional Model for Person Re-identification2017
- Sampling Matters in Deep Embedding Learning2017
- Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation2017
- Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mappingPattern Recognition, 2017
- Deep Residual Learning for Image Recognition2016
- Scalable Person Re-identification: A Benchmark2015
- Person re-identification by Local Maximal Occurrence representation and metric learning2015
- A Review on Multi-Label Learning AlgorithmsIEEE Transactions on Knowledge and Data Engineering, 2013
- ImageNet: A large-scale hierarchical image database2009
- A contextual dissimilarity measure for accurate and efficient image search2007