CRAFT: Concept Recursive Activation FacTorization for Explainability-Reference-Cited by-同舟云学术

CRAFT: Concept Recursive Activation FacTorization for Explainability

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Fel Thomas¹,Picard Agustin²,Bethune Louis²,Boissin Thibaut²,Vigouroux David²,Colin Julien¹,Cadénc Rémi¹,Serre Thomas¹

Affiliation:

1. Carney Institute for Brain Science, Brown University,USA

2. Artificial and Natural Intelligence Toulouse Institute, Université Toulouse,France

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10203037/10203050/10205223.pdf?arnumber=10205223

Reference78 articles.

1. Toy models of superposition;elhage;Transformer Circuits Thread,2022

2. why should i trust you?” explaining the predictions of any classifier;tulio ribeiro;ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,0

3. The approximation of one matrix by another of lower rank

4. Using Data Imputation for Signal Separation in High-contrast Imaging

5. Don't lie to me! robust and efficient explain-ability with verified perturbation analysis;fel;ArXiv Preprint,2022

Cited by 14 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. OCIE: Augmenting model interpretability via Deconfounded Explanation-Guided Learning;Knowledge-Based Systems;2024-10

2. How Explainable AI Affects Human Performance: A Systematic Review of the Behavioural Consequences of Saliency Maps;International Journal of Human–Computer Interaction;2024-07-29

3. Interpretability is in the Eye of the Beholder: Human Versus Artificial Classification of Image Segments Generated by Humans Versus XAI;International Journal of Human–Computer Interaction;2024-03-06

4. Learning Intra-class Multimodal Distributions with Orthonormal Matrices;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03

5. Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03