#concept-activation-vectors News & Analysis

2 articles tagged with #concept-activation-vectors. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AINeutralarXiv – CS AI · Jun 106/10

🧠

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification

Researchers introduce Visual-TCAV, a novel explainability framework for image classification that combines concept-based and saliency-based methods to provide both local and global interpretations of CNN predictions. The method demonstrates improved faithfulness compared to existing approaches like TCAV, bridging a gap between understanding where networks recognize concepts and how those concepts contribute to specific predictions.

AIBullisharXiv – CS AI · May 126/10

🧠

E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability

Researchers introduce E-TCAV, an optimized version of TCAV that improves the efficiency and stability of neural network interpretability testing by leveraging penultimate layer representations. The method achieves linear speed-ups while maintaining accuracy, advancing practical tools for model debugging and real-time concept-guided training across vision and language tasks.