CoDTS: Enhancing Sparsely Supervised Collaborative Perception with a Dual Teacher-Student Framework

TL;DR

CoDTS introduces a dual teacher-student framework with adaptive learning modules to generate high-quality, abundant pseudo labels for sparsely supervised collaborative perception, achieving state-of-the-art results.

Contribution

The paper proposes a novel end-to-end dual teacher-student framework with adaptive modules to improve pseudo label quality and quantity in sparse collaborative perception.

Findings

Achieves a new state-of-the-art performance in sparsely supervised collaborative perception.

Effectively balances pseudo label quality and quantity through adaptive modules.

Demonstrates significant improvements over existing methods in experiments.

Abstract

Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniques and generate pseudo labels for the missing instances. However, these methods fail to achieve an optimal confidence threshold that harmonizes the quality and quantity of pseudo labels. To address this issue, we propose an end-to-end Collaborative perception Dual Teacher-Student framework (CoDTS), which employs adaptive complementary learning to produce both high-quality and high-quantity pseudo labels. Specifically, the Main Foreground Mining (MFM) module generates high-quality pseudo labels based on the prediction of the static teacher. Subsequently, the Supplement Foreground Mining (SFM) module ensures a balance between the quality and quantity of pseudo labels by adaptively identifying missing instances based on the prediction of the dynamic teacher. Additionally, the Neighbor Anchor Sampling (NAS) module is incorporated to enhance the representation of pseudo labels. To promote the adaptive complementary learning, we implement a staged training strategy that trains the student and dynamic teacher in a mutually beneficial manner. Extensive experiments demonstrate that the CoDTS effectively ensures an optimal balance of pseudo labels in both quality and quantity, establishing a new state-of-the-art in sparsely supervised collaborative perception. The code is available at https://github.com/CatOneTwo/CoDTS.