Skip to content
InfoResearchPeer-reviewed

From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models

Published
Record updated
View JSON

Summary

The authors present a unified framework for interpreting vision models that centers on the pointwise feature vector (PFV) paired with its instance-specific Effective Receptive Field (iERF). It combines Sharing Ratio Decomposition (SRD) for local saliency maps, Concept-Anchored Feature Explanation (CAFE) for global semantic labeling of sparse autoencoder latents, and Interlayer Concept Attribution (ICAT) for tracing concept influence across layers. Across ResNet50, VGG16, and ViTs, the framework is reported to outperform baselines in fidelity and robustness.