Learning from Distributed Eyes: Leveraging Collaborative Perception for Automated Model Adaptation

2026-09-16

AI Summary

为解决自动驾驶中感知模型在新环境下的泛化问题，提出LDE框架，利用协同感知生成高质量伪标签以适应模型，设计特征分享、视场过滤和课程学习策略。

Abstract

In autonomous driving, perception models often struggle to generalize to new environments due to domain shifts. While unsupervised model adaptation offers a feasible solution without labor-intensive manual labeling, existing methods that rely solely on the ego-vehicle's data often lead to inferior pseudo-labeling performance. To address this critical issue, we propose LDE, Learning from Distributed ``Eyes", a novel framework that transforms collaborative perception (CP) into a source of high-quality supervision for model adaptation. This pseudo-labeling approach is hyperparameter-insensitive and relatively reliable, assuming CP often outperforms single-agent's perception. However, naively implementing this approach encounters (1) the communication bottleneck of sharing rich features under time and bandwidth constraints, (2) the view discrepancy between the CP view and the learner's Field of View (FoV), and (3) the unreliability even in CP-generated labels. To address these issues, we design an adaptation-oriented feature sharing mechanism that selectively transmits the most critical information for adaptation, an FoV filtering method that meticulously eliminates mismatched labels, and a curriculum learning strategy to progressively exploit pseudo labels. Extensive experiments on 3D object detection tasks demonstrate that LDE consistently outperforms both the pre-trained models and state-of-the-art unsupervised adaptation methods.

Problem

• domain shifts
• unsupervised model adaptation
• pseudo-labeling performance

Innovation

• collaborative perception
• model adaptation
• pseudo-labeling
• feature sharing
• curriculum learning