Showing 2026 · cs.CVShow all
2 papers · 2 filters
cs.CV2026
Seeing Through Distractions: Context-Stable Attribution via the Least Core
Sai Ganesh Nagarajan, Toshinori Yamauchi, Hiroshi Kera
Shapley-value-based explanations are widely used for feature attribution in machine learning. However, in computer vision, a feature may reduce the target-class score when added to…
cs.CV2026
Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions
Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto
Zero-shot textual explanations aim to make image classifiers more transparent by probing their internal representations, without relying on task-specific supervision or LVLMs. Howe…