TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models
Abstract
Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of language models to interpret the learned features of pre-trained image classifiers. Our method, called TExplain, tackles this task by training a neural network to establish a connection between the feature space of image classifiers and language models. Then, during inference, our approach generates a vast number of sentences to explain the features learned by the classifier for a given image. These sentences are then used to extract the most frequent words, providing a comprehensive understanding of the learned features and patterns within the classifier. Our method, for the first time, utilizes these frequent words corresponding to a visual representation to provide insights into the decision-making process of the independently trained classifier, enabling the detection of spurious correlations, biases, and a deeper comprehension of its behavior. To validate the effectiveness of our approach, we conduct experiments on diverse datasets, including ImageNet-9L and Waterbirds. The results demonstrate the potential of our method to enhance the interpretability and robustness of image classifiers.
Cite
@article{arxiv.2309.00733,
title = {TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models},
author = {Saeid Asgari Taghanaki and Aliasghar Khani and Ali Saheb Pasand and Amir Khasahmadi and Aditya Sanghi and Karl D. D. Willis and Ali Mahdavi-Amiri},
journal= {arXiv preprint arXiv:2309.00733},
year = {2024}
}
Comments
Accepted to ICLR 2024, Reliable and Responsible Foundation Models workshop