ReIDTrack: Multi-Object Track and Segmentation Without Motion

TL;DR

This paper introduces a simple, high-performance detection and appearance-based method for multi-object tracking and segmentation that achieves state-of-the-art results without using motion information.

Contribution

The paper demonstrates that high-quality detection and appearance models alone can achieve SOTA performance in MOT and MOTS, removing the need for motion-based association.

Findings

Wins 1st place on MOTS track at CVPR2023 WAD workshop.

Achieves 2nd place on MOT track at CVPR2023 WAD workshop.

Proves effectiveness of detection and appearance models without motion information.

Abstract

In recent years, dominant Multi-object tracking (MOT) and segmentation (MOTS) methods mainly follow the tracking-by-detection paradigm. Transformer-based end-to-end (E2E) solutions bring some ideas to MOT and MOTS, but they cannot achieve a new state-of-the-art (SOTA) performance in major MOT and MOTS benchmarks. Detection and association are two main modules of the tracking-by-detection paradigm. Association techniques mainly depend on the combination of motion and appearance information. As deep learning has been recently developed, the performance of the detection and appearance model is rapidly improved. These trends made us consider whether we can achieve SOTA based on only high-performance detection and appearance model. Our paper mainly focuses on exploring this direction based on CBNetV2 with Swin-B as a detection model and MoCo-v2 as a self-supervised appearance model. Motion information and IoU mapping were removed during the association. Our method wins 1st place on the MOTS track and wins 2nd on the MOT track in the CVPR2023 WAD workshop. We hope our simple and effective method can give some insights to the MOT and MOTS research community. Source code will be released under this git repository