Bag of Tricks for Domain Adaptive Multi-Object Tracking

TL;DR

This paper introduces SIA_Track, a domain adaptive multi-object tracking method that leverages synthetic and unlabeled real data with pseudo-labeling and model aggregation to improve real-world detection performance, winning a challenge.

Contribution

It presents a novel training procedure combining pseudo-labeling, model soups, and cross-domain sampling for improved domain adaptation in multi-object tracking.

Findings

Achieved first place on MOTSynth2MOT17 track at BMTT 2022.

Demonstrated effectiveness of pseudo-labeling and model soups in domain adaptation.

Improved detection performance on real data using synthetic training methods.

Abstract

In this paper, SIA_Track is presented which is developed by a research team from SI Analytics. The proposed method was built from pre-existing detector and tracker under the tracking-by-detection paradigm. The tracker we used is an online tracker that merely links newly received detections with existing tracks. The core part of our method is training procedure of the object detector where synthetic and unlabeled real data were only used for training. To maximize the performance on real data, we first propose to use pseudo-labeling that generates imperfect labels for real data using a model trained with synthetic dataset. After that model soups scheme was applied to aggregate weights produced during iterative pseudo-labeling. Besides, cross-domain mixed sampling also helped to increase detection performance on real data. Our method, SIA_Track, takes the first place on MOTSynth2MOT17 track at BMTT 2022 challenge. The code is available on https://github.com/SIAnalytics/BMTT2022_SIA_track.