arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.05968cs.CVcs.AIcs.LG
收藏

视频Transformer的时空混合注意力

Space-time Mixing Attention for Video Transformer

Samsung AI Cambridge(三星剑桥人工智能中心);Queen Mary University of London(伦敦玛丽女王大学)

Adrian Bulat, Juan-Manuel Perez-Rua, Swathikiran Sudhakaran, Brais Martinez, Georgios Tzimiropoulos

摘要:

本文是关于使用Transformers的视频识别。最近在这一领域的尝试已经证明了有前途的结果方面的识别精度,但他们也被证明,在许多情况下,由于额外的建模的时间信息,导致显着的计算开销。在这项工作中,我们提出了一个视频Transformer模型的复杂性与视频序列中的帧的数量成线性比例,因此不会引起任何开销相比,基于图像的Transformer模型。为了实现这一点,我们的模型做了两个近似的视频Transformers中使用的全时空注意:(a)它限制时间注意到一个本地的时间窗口,并利用Transformer的深度,以获得完整的时间覆盖的视频序列。(b)它使用有效的时空混合来共同关注空间和时间位置,而不会在仅空间注意力模型之上产生任何额外成本。我们还展示了如何整合2个非常轻量级的机制,全球时间只注意,以最小的计算成本提供额外的精度提高。我们证明了我们的模型在最流行的视频识别数据集上产生了非常高的识别精度,同时比其他视频Transformer模型更有效。代码将提供。

英文摘要:

This paper is on video recognition using Transformers. Very recent attempts in this area have demonstrated promising results in terms of recognition accuracy, yet they have been also shown to induce, in many cases, significant computational overheads due to the additional modelling of the temporal information. In this work, we propose a Video Transformer model the complexity of which scales linearly with the number of frames in the video sequence and hence induces no overhead compared to an image-based Transformer model. To achieve this, our model makes two approximations to the full space-time attention used in Video Transformers: (a) It restricts time attention to a local temporal window and capitalizes on the Transformer's depth to obtain full temporal coverage of the video sequence. (b) It uses efficient space-time mixing to attend jointly spatial and temporal locations without inducing any additional cost on top of a spatial-only attention model. We also show how to integrate 2 very lightweight mechanisms for global temporal-only attention which provide additional accuracy improvements at minimal computational cost. We demonstrate that our model produces very high recognition accuracy on the most popular video recognition datasets while at the same time being significantly more efficient than other Video Transformer models. Code will be made available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑