AI RESEARCH
VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
arXiv CS.CV
•
ArXi:2510.00458v2 Announce Type: replace Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt models online using only unlabeled target data. However, despite substantial progress in TTA for vision-language classification, TTA for VLODs remains largely unexplored. The only prior method relies on a mean-teacher framework that