تقرير
TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models
العنوان: | TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models |
---|---|
المؤلفون: | Taghanaki, Saeid Asgari, Khani, Aliasghar, Pasand, Ali Saheb, Khasahmadi, Amir, Sanghi, Aditya, Willis, Karl D. D., Mahdavi-Amiri, Ali |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning |
الوصف: | 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. Comment: Accepted to ICLR 2024, Reliable and Responsible Foundation Models workshop |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2309.00733 |
رقم الأكسشن: | edsarx.2309.00733 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |