Learning Bottleneck Concepts in Image Classification
This work addresses the problem of making AI models more interpretable for users, though it appears incremental as it builds on existing concept-based frameworks.
The paper tackles the challenge of interpreting deep neural networks by proposing Bottleneck Concept Learner (BotCL), a method that learns human-understandable concepts without explicit supervision, and demonstrates its potential to improve interpretability in image classification tasks.
Interpreting and explaining the behavior of deep neural networks is critical for many tasks. Explainable AI provides a way to address this challenge, mostly by providing per-pixel relevance to the decision. Yet, interpreting such explanations may require expert knowledge. Some recent attempts toward interpretability adopt a concept-based framework, giving a higher-level relationship between some concepts and model decisions. This paper proposes Bottleneck Concept Learner (BotCL), which represents an image solely by the presence/absence of concepts learned through training over the target task without explicit supervision over the concepts. It uses self-supervision and tailored regularizers so that learned concepts can be human-understandable. Using some image classification tasks as our testbed, we demonstrate BotCL's potential to rebuild neural networks for better interpretability. Code is available at https://github.com/wbw520/BotCL and a simple demo is available at https://botcl.liangzhili.com/.