Multi-object tracking with self-supervised associating network

TL;DR

This paper introduces a self-supervised learning approach for multi-object tracking that leverages unlabeled short videos to improve re-identification, achieving state-of-the-art results on the MOT17 benchmark.

Contribution

It proposes a novel self-supervised training method for re-identification networks in multi-object tracking, addressing data labeling challenges.

Findings

Achieved state-of-the-art MOTA 62.0% and IDF1 62.6% on MOT17.

Self-supervised training improves tracking performance with more unlabeled data.

Demonstrated potential of self-supervised methods in MOT.

Abstract

Multi-Object Tracking (MOT) is the task that has a lot of potential for development, and there are still many problems to be solved. In the traditional tracking by detection paradigm, There has been a lot of work on feature based object re-identification methods. However, this method has a lack of training data problem. For labeling multi-object tracking dataset, every detection in a video sequence need its location and IDs. Since assigning consecutive IDs to each detection in every sequence is a very labor-intensive task, current multi-object tracking dataset is not sufficient enough to train re-identification network. So in this paper, we propose a novel self-supervised learning method using a lot of short videos which has no human labeling, and improve the tracking performance through the re-identification network trained in the self-supervised manner to solve the lack of training data problem. Despite the re-identification network is trained in a self-supervised manner, it achieves the state-of-the-art performance of MOTA 62.0\% and IDF1 62.6\% on the MOT17 test benchmark. Furthermore, the performance is improved as much as learned with a large amount of data, it shows the potential of self-supervised method.