通过通用概念发现理解视频Transformer

Understanding Video Transformers via Universal Concept Discovery

January 19, 2024

作者: Matthew Kowal, Achal Dave, Rares Ambrus, Adrien Gaidon, Konstantinos G. Derpanis, Pavel Tokmakov

cs.AI

摘要

本文研究了视频的基于概念的Transformer表示的可解释性问题。具体而言，我们试图解释基于高级时空概念的视频Transformer的决策过程，这些概念是自动发现的。先前关于基于概念的可解释性的研究仅集中在图像级任务上。相比之下，视频模型涉及额外的时间维度，增加了复杂性，并在识别随时间变化的动态概念方面提出了挑战。在这项工作中，我们通过引入第一个视频Transformer概念发现（VTCD）算法系统地解决了这些挑战。为此，我们提出了一种有效的方法，用于无监督地识别视频Transformer表示的单元 - 概念，并对其对模型输出的重要性进行排名。得到的概念具有很高的可解释性，揭示了在非结构化视频模型中的时空推理机制和以对象为中心的表示。通过在各种监督和自监督表示上联合进行这种分析，我们发现其中一些机制在视频Transformer中是通用的。最后，我们证明了VTCD可用于改善精细任务的模型性能。

English

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 demonstrate that VTCDcan be used to improve model performance for fine-grained tasks.