Describe-and-Dissect: Interpreting Neurons in Vision Networks with Language Models

23 Sept 2023 (modified: 11 Feb 2024)Submitted to ICLR 2024EveryoneRevisionsBibTeX
Primary Area: visualization or interpretation of learned representations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Interpretability, Explainability, Deep Learning
Submission Guidelines: I certify that this submission complies with the submission instructions as described on
TL;DR: We propose an automated method to generate comprehensive descriptions of representations of neurons in the deep neural networks
Abstract: In this paper, we propose Describe-and-Dissect, a novel method to describe the roles of hidden neurons in vision networks. Describe-and-Dissect utilizes recent advancements in multimodal deep learning to produce complex natural language descriptions, without the need for labeled training data or a predefined set of concepts to choose from. Additionally, Describe-and-Dissect is training-free, meaning we don't train any new models and can easily leverage more capable general purpose models in the future. We show on a large scale user study that our method outperforms the state-of-the-art baseline methods including CLIP-Dissect, MILAN, and Network Dissection. Our method on average provides the highest quality labels and is more than 2$\times$ as likely to be selected as the best explanation for a neuron than the best baseline.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6902