CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation

TL;DR

This paper introduces CML-MOTS, a collaborative multi-task learning framework that simultaneously performs object detection, segmentation, and tracking in videos, improving multi-object video analysis for applications like autonomous driving.

Contribution

The paper proposes a novel end-to-end CNN with associative connections enabling collaborative learning across detection, segmentation, and tracking tasks, enhancing multi-object video analysis.

Findings

Achieved encouraging results on KITTI MOTS and MOTS Challenge datasets.

Demonstrated improved performance through information sharing among tasks.

Validated effectiveness of the collaborative multi-task learning approach.

Abstract

The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and segment multiple objects in video frames, has drawn much attention for its potential applications in various emerging areas such as autonomous driving, intelligent transportation, and smart retail. In this paper, we propose an effective framework for instance-level visual analysis on video frames, which can simultaneously conduct object detection, instance segmentation, and multi-object tracking. The core idea of our method is collaborative multi-task learning which is achieved by a novel structure, named associative connections among detection, segmentation, and tracking task heads in an end-to-end learnable CNN. These additional connections allow information propagation across multiple related tasks, so as to benefit these tasks simultaneously. We evaluate the proposed method extensively on KITTI MOTS and MOTS Challenge datasets and obtain quite encouraging results.