Simple Unsupervised Multi-Object Tracking

TL;DR

This paper introduces SimpleReID, an unsupervised re-identification network for multi-object tracking that eliminates the need for annotated datasets, achieving state-of-the-art results on popular benchmarks.

Contribution

It proposes a novel unsupervised ReID training method using unlabeled videos and demonstrates competitive performance without tracking supervision.

Findings

SimpleReID outperforms simpler unsupervised alternatives.

Achieves state-of-the-art on MOT16/17 datasets without supervision.

Unsupervised ReID performs well even in crowded and occluded scenarios.

Abstract

Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets. In this work, we remove the need for annotated datasets by proposing an unsupervised re-identification network, thus sidestepping the labeling costs entirely, required for training. Given unlabeled videos, our proposed method (SimpleReID) first generates tracking labels using SORT and trains a ReID network to predict the generated labels using crossentropy loss. We demonstrate that SimpleReID performs substantially better than simpler alternatives, and we recover the full performance of its supervised counterpart consistently across diverse tracking frameworks. The observations are unusual because unsupervised ReID is not expected to excel in crowded scenarios with occlusions, and drastic viewpoint changes. By incorporating our unsupervised SimpleReID with CenterTrack trained on augmented still images, we establish a new state-of-the-art performance on popular datasets like MOT16/17 without using tracking supervision, beating current best (CenterTrack) by 0.2-0.3 MOTA and 4.4-4.8 IDF1 scores. We further provide evidence for limited scope for improvement in IDF1 scores beyond our unsupervised ReID in the studied settings. Our investigation suggests reconsideration towards more sophisticated, supervised, end-to-end trackers by showing promise in simpler unsupervised alternatives.