Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id

TL;DR

This paper introduces a hybrid dynamic contrast and probability distillation approach for unsupervised person re-identification, effectively utilizing all data points and improving robustness over existing clustering-based methods.

Contribution

It proposes a unified local-to-global contrastive learning framework combined with probability distillation, addressing clustering errors and leveraging all instances in unsupervised Re-Id.

Findings

Achieves superior performance over state-of-the-art methods

Effective in both purely unsupervised and domain adaptation settings

Utilizes self-supervised signals from clustered and unclustered data

Abstract

Unsupervised person re-identification (Re-Id) has attracted increasing attention due to its practical application in the read-world video surveillance system. The traditional unsupervised Re-Id are mostly based on the method alternating between clustering and fine-tuning with the classification or metric learning objectives on the grouped clusters. However, since person Re-Id is an open-set problem, the clustering based methods often leave out lots of outlier instances or group the instances into the wrong clusters, thus they can not make full use of the training samples as a whole. To solve these problems, we present the hybrid dynamic cluster contrast and probability distillation algorithm. It formulates the unsupervised Re-Id problem into an unified local-to-global dynamic contrastive learning and self-supervised probability distillation framework. Specifically, the proposed method can make the utmost of the self-supervised signals of all the clustered and un-clustered instances, from both the instances' self-contrastive level and the probability distillation respective, in the memory-based non-parametric manner. Besides, the proposed hybrid local-to-global contrastive learning can take full advantage of the informative and valuable training examples for effective and robust training. Extensive experiment results show that the proposed method achieves superior performances to state-of-the-art methods, under both the purely unsupervised and unsupervised domain adaptation experiment settings.