Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
A Good Initialization is All You Need for Faithful Visual Attribution
Zihan Gu, Jiayu Wang, Hua Zhang +1
Faithful visual attribution identifies which image regions support a model prediction. Search-based perturbation methods lead the insertion--deletion faithfulness frontier by maski…
cs.CV2026
PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution
Zihan Gu, Junchi Zhang, Li Liu +2
Visual attribution is a fundamental tool for interpreting modern vision and vision-language models, particularly when their decisions must be inspected, diagnosed, or audited. Its…
cs.CV2025
PhaseWin Search Framework Enable Efficient Object-Level Interpretation
Zihan Gu, Ruoyu Chen, Junchi Zhang +3
Attribution is essential for interpreting object-level foundation models. Recent methods based on submodular subset selection have achieved high faithfulness, but their efficiency…