16 papers
Ill-Posed by Design: Probing Evidence Use in VLMs
Boaz Meivar, Shaked Perek, Shani Shvartzman +2
Counterfactual analysis is widely used to study evidence use in vision-language models, but its diagnostic value is limited on well-posed tasks: when several cues independently sup…
Where Does Texture Evidence Live in SAM? Features, Proposal Masks, and Texture Segmentation
Nadav Orenstein, Aviad Cohen Zada, Shai Avidan +1
Texture segmentation stresses foundation segmentation because meaningful regions are defined by material or repeated appearance rather than object identity. Segment Anything Models…
Sub-Semantic Image Segmentation
Aviad Cohen Zada, Nadav Orenstein, Shai Avidan +1
Images can be segmented based on visual cues (i.e., texture segmentation) or into objects (i.e., semantic segmentation). We propose a new category of sub-semantic image segmentatio…
Optimal Transport Flow Matching by Design
Shimon Malnick, Matan Rusanovsky, Ohad Fried +1
Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution. When prior-data pairs are coupled via optimal transport (OT), the l…
Scene Grounding In the Wild
Tamir Cohen, Leo Segre, Shay Shomer-Chai +2
Reconstructing accurate 3D models of large-scale real-world scenes from unstructured, in-the-wild imagery remains a core challenge in computer vision, especially when the input vie…
Edge Weight Prediction For Category-Agnostic Pose Estimation
Or Hirschorn, Shai Avidan
Category-Agnostic Pose Estimation (CAPE) localizes keypoints across diverse object categories with a single model, using one or a few annotated support images. Recent works have sh…