works on
concept activation vectors 1concept-based explanations 1contrastive attribution 1embedding perturbation 1explainability 1explainable AI 1image classification 1image similarity 1representation learning 1visual concepts 1

From the 2 of 3 linked papers with an AI index.

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Explaining Image Similarity with Automatically Extracted Concept Activation Vectors

Isaac Roberts, Petra Bevandic, Alexander Schulz +1

The paper proposes a model‑agnostic method that uses automatically discovered concept activation vectors to explain why two images are considered similar, by perturbing embeddings…