Simple Unsupervised Multi-Object Tracking

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.

References in corpus (9)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Simple Online and Realtime Tracking
• MOT16: A Benchmark for Multi-Object Tracking
• Deep Learning in Video Multi-Object Tracking: A Survey
• MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• Similarity Mapping with Enhanced Siamese Network for Multi-Object Tracking
• Refinements in Motion and Appearance for Online Multi-Object Tracking

Cited by in corpus (9)

• MAT: Motion-Aware Multi-Object Tracking
• SDOF-Tracker: Fast and Accurate Multiple Human Tracking by Skipped-Detection and Optical-Flow
• Learning a Proposal Classifier for Multiple Object Tracking
• Local Metrics for Multi-Object Tracking
• Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking
• Self-Supervised Multi-Object Tracking with Cross-Input Consistency
• Learning data association without data association: An EM approach to neural assignment prediction
• Localization-Based Tracking
• Multi-object tracking with self-supervised associating network