CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
This provides a tool for researchers and practitioners to interpret neural networks in computer vision, though it is incremental as it builds on existing multimodal models.
The paper tackles the problem of automatically describing the function of individual hidden neurons in deep vision networks, proposing CLIP-Dissect, which uses multimodal vision/language models to label neurons without labeled data, resulting in more accurate descriptions than existing methods and being over 10 times faster, labeling all neurons from five layers of ResNet-50 in just 4 minutes.
In this paper, we propose CLIP-Dissect, a new technique to automatically describe the function of individual hidden neurons inside vision networks. CLIP-Dissect leverages recent advances in multimodal vision/language models to label internal neurons with open-ended concepts without the need for any labeled data or human examples. We show that CLIP-Dissect provides more accurate descriptions than existing methods for last layer neurons where the ground-truth is available as well as qualitatively good descriptions for hidden layer neurons. In addition, our method is very flexible: it is model agnostic, can easily handle new concepts and can be extended to take advantage of better multimodal models in the future. Finally CLIP-Dissect is computationally efficient and can label all neurons from five layers of ResNet-50 in just 4 minutes, which is more than 10 times faster than existing methods. Our code is available at https://github.com/Trustworthy-ML-Lab/CLIP-dissect. Finally, crowdsourced user study results are available at Appendix B to further support the effectiveness of our method.