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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Taghanaki, Saeid Asgari, Khani, Aliasghar, Pasand, Ali Saheb, Khasahmadi, Amir, Sanghi, Aditya, Willis, Karl D. D., Mahdavi-Amiri, Ali
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910430695260160
author Taghanaki, Saeid Asgari
Khani, Aliasghar
Pasand, Ali Saheb
Khasahmadi, Amir
Sanghi, Aditya
Willis, Karl D. D.
Mahdavi-Amiri, Ali
author_facet Taghanaki, Saeid Asgari
Khani, Aliasghar
Pasand, Ali Saheb
Khasahmadi, Amir
Sanghi, Aditya
Willis, Karl D. D.
Mahdavi-Amiri, Ali
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_00733
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models
Taghanaki, Saeid Asgari
Khani, Aliasghar
Pasand, Ali Saheb
Khasahmadi, Amir
Sanghi, Aditya
Willis, Karl D. D.
Mahdavi-Amiri, Ali
Computer Vision and Pattern Recognition
Machine Learning
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.
title TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2309.00733