Concept Activation Vectors

Also known as CAV

Follow this topic Ask about this topic

Latest papers

8 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution
Oct 3, 2026Yehonatan Elisha, Oren Barkan, Ziv Weiss Haddad +1Concept Activation Vectors Concept-Based Explanations
Tel Aviv University · The Open University
ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers
Sep 5, 2026Effrosyni Sokli, Isaac Roberts, Alexander Schulz +2Concept Activation Vectors Interpretable ML
Department of Informatics, Systems and Communication, DISCo University of Milano-Bicocca Milan, Italy · CITEC - Center for Cognitive Interaction Technology Bielefeld University Bielefeld, Germany
Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors
Aug 6, 2026Arya Labroo, Mengjie Qian, Kate KnillLanguage Model Bias Evaluation Concept Activation Vectors
University of Cambridge
Explaining Image Similarity with Automatically Extracted Concept Activation Vectors
Jul 30, 2026Isaac Roberts, Petra Bevandic, Alexander Schulz +1Concept-Based Explanations Concept Activation Vectors
Bielefeld University - Faculty of Technology · University of Zagreb - Faculty of Electrical Engineering and Computing
Causal Physics Steering in Video World Models via Concept Activation Vectors
May 23, 2026Nahid AlamTransformer Interpretability Concept Activation Vectors
Oreon Labs, Cohere Labs Community
SwordBench: Evaluating Orthogonality of Steering Image Representations
May 10, 2026Vladimir Zaigrajew, Dawid Pludowski, Hubert Baniecki +1Vision Foundation Models Representation Engineering
Centre for Credible AI Warsaw University of Technology Warsaw, Poland · University of Warsaw Warsaw, Poland
Scalable and Explainable Learner-Video Interaction Prediction using Multimodal Large Language Models
Apr 6, 2026Dominik Glandorf, Fares Fawzi, Tanja KäserConcept Activation Vectors Video Understanding
EPFL, Switzerland
On The Variability of Concept Activation Vectors
Sep 28, 2025Julia Wenkmann, Damien GarreauConcept Activation Vectors Explainable Artificial Intelligence
Universität Würzburg, CAIDAS

Oct 3, 2026J/K move · Enter open · S save

ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution

Yehonatan Elisha, Oren Barkan, Ziv Weiss Haddad, Noam Koenigstein

Tel Aviv University · The Open University

Concept Activation Vectors Concept-Based Explanations Explainable Image Classification Saliency Map Evaluation

Open paper AskPDF arXiv

Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful concepts, limiting their interpretability and trustworthiness. We introduce Concept-based Explanations (ConEx), a novel framework that bridges saliency visualization with concept-based reasoning to provide both faithfulness and interpretability. ConEx automatically discovers class-specific concepts and represents them through concept activation vectors (CAVs), learned without manual supervision using an architecture-specific masking mechanism that reduces noise introduced by the segmentation masks to enhance concept purity. ConEx generates faithful saliency maps that reveal where each concept appears in the image and how it contributes to the prediction. To evaluate the reliability of these learned concepts, we propose two complementary metrics, Vector-Concept Match (VCM) and Concept-Class Match (CCM), that quantify concept alignment and enable direct comparison with existing methods. Extensive experiments across diverse settings demonstrate that ConEx achieves state-of-the-art performance on faithfulness, segmentation, and concept-quality benchmarks. Overall, ConEx advances the field toward truly interpretable and concept-grounded explanations in vision models.