Model-Agnostic Multi-Agent Perception Framework

TL;DR

This paper introduces a model-agnostic multi-agent perception framework that calibrates confidence scores and aggregates bounding boxes to improve 3D object detection across heterogeneous agents without sharing model details.

Contribution

It presents a novel confidence calibration method and a bounding box aggregation algorithm that enhance multi-agent perception performance without requiring model sharing.

Findings

Improved 3D detection accuracy across heterogeneous agents

Effective confidence calibration reduces model mismatch effects

Framework maintains model privacy while enhancing perception performance

Abstract

Existing multi-agent perception systems assume that every agent utilizes the same model with identical parameters and architecture. The performance can be degraded with different perception models due to the mismatch in their confidence scores. In this work, we propose a model-agnostic multi-agent perception framework to reduce the negative effect caused by the model discrepancies without sharing the model information. Specifically, we propose a confidence calibrator that can eliminate the prediction confidence score bias. Each agent performs such calibration independently on a standard public database to protect intellectual property. We also propose a corresponding bounding box aggregation algorithm that considers the confidence scores and the spatial agreement of neighboring boxes. Our experiments shed light on the necessity of model calibration across different agents, and the results show that the proposed framework improves the baseline 3D object detection performance of heterogeneous agents.