2 papers
cs.CV2026
PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation
Minjae Lee, Sungwoo Hur, Soojin Hwang +1
Visual Foundation Models (VFMs) such as the Segment Anything Model (SAM) have significantly advanced broad use of image segmentation. However, SAM and its variants necessitate subs…
cs.CV2024
Extract Free Dense Misalignment from CLIP
JeongYeon Nam, Jinbae Im, Wonjae Kim +1
Recent vision-language foundation models still frequently produce outputs misaligned with their inputs, evidenced by object hallucination in captioning and prompt misalignment in t…