Contrastive Learning for Multi-Object Tracking with Transformers

Abstract

The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to perform Multi-Object Tracking (MOT), resulting in more complicated architectures. We instead show how DETR can be turned into a MOT model by employing an instance-level contrastive loss, a revised sampling strategy and a lightweight assignment method. Our training scheme learns object appearances while preserving detection capabilities and with little overhead. Its performance surpasses the previous state-of-the-art by +2.6 mMOTA on the challenging BDD100K dataset and is comparable to existing transformer-based methods on the MOT17 dataset.

arXiv commentWACV 2024

References in corpus (7)

• YOLOX: Exceeding YOLO Series in 2021
• FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
• MOT16: A Benchmark for Multi-Object Tracking
• HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
• CrowdHuman: A Benchmark for Detecting Human in a Crowd
• TransTrack: Multiple Object Tracking with Transformer
• End-to-end Tracking with a Multi-query Transformer