CRAFT: Concept Recursive Activation FacTorization for Explainability
Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023 Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explainability method. However, re...
Saved in:
Main Authors | , , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
17.11.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Proceedings of the IEEE / CVF Computer Vision and Pattern
Recognition Conference (CVPR), 2023 Attribution methods, which employ heatmaps to identify the most influential
regions of an image that impact model decisions, have gained widespread
popularity as a type of explainability method. However, recent research has
exposed the limited practical value of these methods, attributed in part to
their narrow focus on the most prominent regions of an image -- revealing
"where" the model looks, but failing to elucidate "what" the model sees in
those areas. In this work, we try to fill in this gap with CRAFT -- a novel
approach to identify both "what" and "where" by generating concept-based
explanations. We introduce 3 new ingredients to the automatic concept
extraction literature: (i) a recursive strategy to detect and decompose
concepts across layers, (ii) a novel method for a more faithful estimation of
concept importance using Sobol indices, and (iii) the use of implicit
differentiation to unlock Concept Attribution Maps.
We conduct both human and computer vision experiments to demonstrate the
benefits of the proposed approach. We show that the proposed concept importance
estimation technique is more faithful to the model than previous methods. When
evaluating the usefulness of the method for human experimenters on a
human-centered utility benchmark, we find that our approach significantly
improves on two of the three test scenarios. Our code is freely available at
github.com/deel-ai/Craft. |
---|---|
DOI: | 10.48550/arxiv.2211.10154 |