Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
- 29 October 2024
- book chapter
- Published by Springer Nature
- p. 444-461
Abstract
No abstract availableKeywords
All Related Versions
This publication has 29 references indexed in Scilit:
- DeViL: Decoding Vision features into Language2024
- From attribution maps to human-understandable explanations through Concept Relevance PropagationNature Machine Intelligence, 2023
- Towards Better Understanding Attribution Methods2022
- Concept Bottleneck Model With Additional Unsupervised ConceptsIEEE Access, 2022
- Interpretable Basis Decomposition for Visual Explanation2018
- Network Dissection: Quantifying Interpretability of Deep Visual Representations2017
- Generating Visual Explanations2016
- Deep Residual Learning for Image Recognition2016
- The SUN Attribute Database: Beyond Categories for Deeper Scene UnderstandingInternational Journal of Computer Vision, 2014
- ImageNet: A large-scale hierarchical image database2009