CoRA: A Collaborative Robust Architecture with Hybrid Fusion for Efficient Perception

TL;DR

CoRA is a novel architecture for collaborative perception that combines feature-level fusion and object-level correction to enhance robustness and efficiency under adverse communication conditions.

Contribution

It introduces a hybrid fusion approach that decouples performance from robustness, improving efficiency and resilience in collaborative perception systems.

Findings

Improves AP@0.7 by ~19% under extreme scenarios

Reduces communication volume by over 5x

Demonstrates robustness against pose errors

Abstract

Collaborative perception has garnered significant attention as a crucial technology to overcome the perceptual limitations of single-agent systems. Many state-of-the-art (SOTA) methods have achieved communication efficiency and high performance via intermediate fusion. However, they share a critical vulnerability: their performance degrades under adverse communication conditions due to the misalignment induced by data transmission, which severely hampers their practical deployment. To bridge this gap, we re-examine different fusion paradigms, and recover that the strengths of intermediate and late fusion are not a trade-off, but a complementary pairing. Based on this key insight, we propose CoRA, a novel collaborative robust architecture with a hybrid approach to decouple performance from robustness with low communication. It is composed of two components: a feature-level fusion branch and an object-level correction branch. Its first branch selects critical features and fuses them efficiently to ensure both performance and scalability. The second branch leverages semantic relevance to correct spatial displacements, guaranteeing resilience against pose errors. Experiments demonstrate the superiority of CoRA. Under extreme scenarios, CoRA improves upon its baseline performance by approximately 19% in AP@0.7 with more than 5x less communication volume, which makes it a promising solution for robust collaborative perception.