CVJul 24, 2025

DATA: Domain-And-Time Alignment for High-Quality Feature Fusion in Collaborative Perception

arXiv:2507.18237v2h-index: 4Has Code
Originality Highly original
AI Analysis

This work addresses feature quality issues in collaborative perception for autonomous systems, representing an incremental improvement with novel modules for alignment.

The paper tackles the problem of domain gaps and temporal misalignment in collaborative perception, which degrade feature quality for fusion, and demonstrates that their DATA network achieves state-of-the-art performance on three datasets while maintaining robustness under severe delays and errors.

Feature-level fusion shows promise in collaborative perception (CP) through balanced performance and communication bandwidth trade-off. However, its effectiveness critically relies on input feature quality. The acquisition of high-quality features faces domain gaps from hardware diversity and deployment conditions, alongside temporal misalignment from transmission delays. These challenges degrade feature quality with cumulative effects throughout the collaborative network. In this paper, we present the Domain-And-Time Alignment (DATA) network, designed to systematically align features while maximizing their semantic representations for fusion. Specifically, we propose a Consistency-preserving Domain Alignment Module (CDAM) that reduces domain gaps through proximal-region hierarchical downsampling and observability-constrained discriminator. We further propose a Progressive Temporal Alignment Module (PTAM) to handle transmission delays via multi-scale motion modeling and two-stage compensation. Building upon the aligned features, an Instance-focused Feature Aggregation Module (IFAM) is developed to enhance semantic representations. Extensive experiments demonstrate that DATA achieves state-of-the-art performance on three typical datasets, maintaining robustness with severe communication delays and pose errors. The code will be released at https://github.com/ChengchangTian/DATA.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes