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.
Abstract
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 publicationAssociated Researchers
Saeid Asgari
Former Autodesk
Ali Mahdavi-Amiri
School of Computing Science, Simon Fraser University
Related Resources
2023
Neural Shape Diameter Function for Efficient Mesh SegmentationIntroducing a neural approximation of the Shape Diameter Function,…
2023
Generative design for COVID-19 and future pathogens using stochastic multi-agent simulationProposing a generative design workflow that integrates a stochastic…
2022
MaskTune: Mitigating Spurious Correlations by Forcing to ExploreThis work proposes a masking strategy that prevents over-reliance on…
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