Beyond Mean Foils: Auditing Worst-Foil Specificity in Frozen CLIP Region Explanations

arXiv:2609.27356 · cs.CV · Submitted 2026-09-23 · Read on arXiv

cs.CV

Submitted: 2026-09-23

Updated: 2026-09-23

Terminology

• International Conference on Learning Representations — 2× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Cluster-based Concept Importance — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach
• From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
• Contrastive Corpus Attribution for Explaining Representations
• CASE: Contrastive Activation for Class-Sensitive Explanations

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models