AI RESEARCH
DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection
arXiv CS.CV
•
ArXi:2603.18757v1 Announce Type: new Domain Adaptive Object Detection (DAOD) aims to transfer detectors from a labeled source domain to an unlabeled target domain. Existing DAOD methods employ multi-granularity feature alignment to learn domain-invariant representations. However, the local connectivity of their CNN-based backbone and detection head restricts alignment to local regions, failing to extract global domain-invariant features.