International Conference on Learning Representations (ICLR)

Learned Visual Features to Textual Explanations

TExplain projects learned visual representations of a frozen image classifier onto a space that an independently trained language model can interpret. Using a large number of generated sentence samples along with the visual representation, TExplain produces a word cloud for each visual representation. Blue and green refers to frozen and trainable parameters, respectively. The category of the feature representation is highlighted in red, while other captured features are shown in gray. The font size of each word indicates the strength of its corresponding feature.


Learned Visual Features to Textual Explanations

Saeid Asgari Taghanaki, Aliasghar Khani, Amir Khasahmadi, Aditya Sanghi, Karl D.D. Willis, Ali Mahdavi-Amiri

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 large language models (LLMs) 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 LLMs. 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.

Download publication

Associated Researchers

Aliasghar Khani

School of Computing Science, Simon Fraser University

Ali Mahdavi-Amiri

School of Computing Science, Simon Fraser University

View all researchers

Related Resources



Generative Design through Quality-Diversity Data Synthesis and Language Models

A new paradigm for AEC design exploration, based on a combination of…



TimeTunnel: Integrating Spatial and Temporal Motion Editing for Character Animation in Virtual Reality

This research provides an approachable editing experience by…



RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifiers

The 3D deep learning community has seen significant strides in…



Programming and Controlling Self-Folding Robots

This paper describes a robot in the form of a self-folding sheet that…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us