AI RESEARCH
Revisiting Cross-Attention Mechanisms: Leveraging Beneficial Noise for Domain-Adaptive Learning
arXiv CS.CV
•
ArXi:2603.17474v1 Announce Type: new Unsupervised Domain Adaptation (UDA) seeks to transfer knowledge from a labeled source domain to an unlabeled target domain but often suffers from severe domain and scale gaps that degrade performance. Existing cross-attention-based transformers can align features across domains, yet they struggle to preserve content semantics under large appearance and scale variations. To explicitly address these challenges, we