-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kowal_2024_CVPR, author = {Kowal, Matthew and Dave, Achal and Ambrus, Rares and Gaidon, Adrien and Derpanis, Konstantinos G. and Tokmakov, Pavel}, title = {Understanding Video Transformers via Universal Concept Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10946-10956} }
Understanding Video Transformers via Universal Concept Discovery
Abstract
This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely we seek to explain the decision-making process of video transformers based on high-level spatiotemporal concepts that are automatically discovered. Prior research on concept-based interpretability has concentrated solely on image-level tasks. Comparatively video models deal with the added temporal dimension increasing complexity and posing challenges in identifying dynamic concepts over time. In this work we systematically address these challenges by introducing the first Video Transformer Concept Discovery (VTCD) algorithm. To this end we propose an efficient approach for unsupervised identification of units of video transformer representations - concepts and ranking their importance to the output of a model. The resulting concepts are highly interpretable revealing spatio-temporal reasoning mechanisms and object-centric representations in unstructured video models. Performing this analysis jointly over a diverse set of supervised and self-supervised representations we discover that some of these mechanism are universal in video transformers. Finally we show that VTCD can be used for fine-grained action recognition and video object segmentation.
Related Material