CVLGSep 1, 2023

TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models

arXiv:2309.00733v4
Originality Incremental advance
AI Analysis

This addresses the problem of interpretability in vision models for researchers and practitioners, offering a novel approach but with incremental improvements in explanation generation.

The authors tackled the challenge of interpreting learned features in vision models by proposing TExplain, a method that uses pre-trained language models to generate explanations for image classifier features, enabling detection of spurious correlations and biases, with validation on datasets like ImageNet-9L and Waterbirds showing enhanced interpretability and robustness.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes