arXiv cs.CV
· Papers
Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method
arXiv:2603.27556v2 Announce Type: replace Abstract: Open-Vocabulary Object Detection (OVOD) has achieved remarkable success in generalizing to novel categories. However, this success often rests on the implicit assumption of domain stationarity. In this work, we revisit the OVOD paradigm and study a key vulnerability: