站内快照 · 国内可打开。外网原文可能无法访问。
- 论文公开站arXiv
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpret classification and regressio