AI RESEARCH
PrAda: Few-Shot Visual Adaptation for Text-Prompted Segmentation
arXiv CS.CV
•
ArXi:2605.19623v1 Announce Type: new Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guided by textual prompts, without annotations from the target domain. Yet, on specialized target domains, far from the original pre-