BOLT: Online Lightweight Adaptation for Preparation-Free Heterogeneous Cooperative Perception

TL;DR

This paper introduces BOLT, a lightweight online module that enables preparation-free heterogeneous cooperative perception by adapting features via ego-as-teacher distillation, significantly improving detection accuracy without prior training.

Contribution

BOLT is a novel plug-and-play adaptation module that enhances cooperative perception in preparation-free settings using ego-based distillation and feature alignment.

Findings

BOLT improves AP@50 by up to 32.3 points over unadapted fusion.

It outperforms ego-only perception on DAIR-V2X and OPV2V datasets.

BOLT requires only 0.9M trainable parameters.

Abstract

Most existing heterogeneous cooperative perception methods depend on prior preparation like offline joint training or tailored collaborator-model adaptation. Such preprocessing is, however, generally impractical in real scenarios, as agents are usually independently trained by different developers and meet occasionally online. This work investigates \emph{preparation-free heterogeneous cooperative perception}, where agents use independently trained single-agent detectors without any pre-deployment coordination. We find direct cross-agent fusion under this setting greatly underperforms ego-only perception. We present BOLT, a lightweight plug-and-play module that adapts neighboring features online via ego-as-teacher distillation, requiring only ego predictions without ground-truth labels. BOLT leverages high-confidence ego perception features to guide cross-agent feature-domain alignment, while enabling neighbors to contribute features in the ego's low-confidence regions. With only 0.9M trainable parameters, BOLT improves AP@50 by up to 32.3 points over vanilla unadapted fusion in the preparation-free setting. It consistently outperforms ego-only results on DAIR-V2X and OPV2V, across different encoder pairs and fusion strategies. Code: https://github.com/sidiangongyuan/BOLT.