Learning of global objective for network flow in multi-object tracking

Shuai Li, Yu Kong, Hamid Rezatofighi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

This paper concerns the problem of multi-object tracking based on the min-cost flow (MCF) formulation, which is conventionally studied as an instance of linear program. Given its computationally tractable inference, the success of MCF tracking largely relies on the learned cost function of underlying linear program. Most previous studies focus on learning the cost function by only taking into account two frames during training, therefore the learned cost function is sub-optimal for MCF where a multi-frame data association must be considered during inference. In order to address this problem, in this paper we propose a novel differentiable framework that ties training and inference together during learning by solving a bi-level optimization problem, where the lower-level solves a linear program and the upper-level contains a loss function that incorporates global tracking result. By back-propagating the loss through differentiable layers via gradient descent, the globally parameterized cost function is explicitly learned and regularized. With this approach, we are able to learn a better objective for global MCF tracking. As a result, we achieve competitive performances compared to the current state-of-the-art methods on the popular multi-object tracking benchmarks such as MOT16, MOT17 and MOT20
Original languageEnglish
Title of host publicationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
EditorsKristin Dana, Gang Hua, Stefan Roth, Dimitris Samaras, Richa Singh
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages8855-8865
Number of pages11
Publication statusPublished - 2022
EventIEEE Conference on Computer Vision and Pattern Recognition 2022 - New Orleans, United States of America
Duration: 19 Jun 202224 Sep 2022
https://cvpr2022.thecvf.com/ (Website)
https://ieeexplore.ieee.org/xpl/conhome/9878378/proceeding (Proceedings)

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition 2022
Abbreviated titleCVPR 2022
Country/TerritoryUnited States of America
CityNew Orleans
Period19/06/2224/09/22
Internet address

Cite this