AI RESEARCH
Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges
arXiv CS.CV
•
ArXi:2604.08230v1 Announce Type: new Object detection models trained on a source domain often exhibit significant performance degradation when deployed in unseen target domains, due to various kinds of variations, such as sensing conditions, environments and data distributions. Hence, regardless the recent breakthrough advances in deep learning-based detection technology, cross-domain object detection (CDOD) remains a critical research area.