CollaMamba: Efficient Collaborative Perception with Cross-Agent Spatial-Temporal State Space Model

TL;DR

CollaMamba introduces a resource-efficient spatial-temporal state space model for multi-agent collaborative perception, significantly improving accuracy while reducing computational and communication costs.

Contribution

It proposes a novel cross-agent spatial-temporal state space model with a backbone and history-aware module, enabling efficient long-range feature modeling with low overhead.

Findings

Outperforms state-of-the-art methods in accuracy.

Reduces computational overhead by up to 71.9%.

Decreases communication costs to 1/64 of previous methods.

Abstract

By sharing complementary perceptual information, multi-agent collaborative perception fosters a deeper understanding of the environment. Recent studies on collaborative perception mostly utilize CNNs or Transformers to learn feature representation and fusion in the spatial dimension, which struggle to handle long-range spatial-temporal features under limited computing and communication resources. Holistically modeling the dependencies over extensive spatial areas and extended temporal frames is crucial to enhancing feature quality. To this end, we propose a resource efficient cross-agent spatial-temporal collaborative state space model (SSM), named CollaMamba. Initially, we construct a foundational backbone network based on spatial SSM. This backbone adeptly captures positional causal dependencies from both single-agent and cross-agent views, yielding compact and comprehensive intermediate features while maintaining linear complexity. Furthermore, we devise a history-aware feature boosting module based on temporal SSM, extracting contextual cues from extended historical frames to refine vague features while preserving low overhead. Extensive experiments across several datasets demonstrate that CollaMamba outperforms state-of-the-art methods, achieving higher model accuracy while reducing computational and communication overhead by up to 71.9% and 1/64, respectively. This work pioneers the exploration of the Mamba's potential in collaborative perception. The source code will be made available.