Tracking without Label: Unsupervised Multiple Object Tracking via Contrastive Similarity Learning

TL;DR

This paper introduces UCSL, an unsupervised contrastive learning approach for multiple object tracking that leverages feature consistency across frames to improve accuracy without relying on labels.

Contribution

It proposes a novel unsupervised contrastive framework with three modules to enhance object representation and association in MOT without supervision.

Findings

Outperforms existing unsupervised MOT methods.

Achieves higher accuracy than some fully supervised methods.

Effectively mitigates occlusion and ambiguity issues.

Abstract

Unsupervised learning is a challenging task due to the lack of labels. Multiple Object Tracking (MOT), which inevitably suffers from mutual object interference, occlusion, etc., is even more difficult without label supervision. In this paper, we explore the latent consistency of sample features across video frames and propose an Unsupervised Contrastive Similarity Learning method, named UCSL, including three contrast modules: self-contrast, cross-contrast, and ambiguity contrast. Specifically, i) self-contrast uses intra-frame direct and inter-frame indirect contrast to obtain discriminative representations by maximizing self-similarity. ii) Cross-contrast aligns cross- and continuous-frame matching results, mitigating the persistent negative effect caused by object occlusion. And iii) ambiguity contrast matches ambiguous objects with each other to further increase the certainty of subsequent object association through an implicit manner. On existing benchmarks, our method outperforms the existing unsupervised methods using only limited help from ReID head, and even provides higher accuracy than lots of fully supervised methods.