Learning of Global Objective for Network Flow in Multi-Object Tracking

TL;DR

This paper introduces a differentiable bi-level optimization framework that jointly learns the cost function and performs multi-frame data association for multi-object tracking, leading to improved tracking accuracy.

Contribution

It proposes a novel differentiable training method that integrates inference into learning, optimizing the cost function for multi-object tracking using global information.

Findings

Achieves competitive results on MOT benchmarks.

Effectively learns a global objective for multi-frame data association.

Outperforms previous methods with sub-optimal cost functions.

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.