A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

Christoph Feichtenhofer, Haoqi Fan, Bo Xiong, Ross Girshick, Kaiming He; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 3299-3309

Abstract


We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to space-time. Our objective encourages temporally-persistent features in the same video, and in spite of its simplicity, it works surprisingly well across: (i) different unsupervised frameworks, (ii) pre-training datasets, (iii) downstream datasets, and (iv) backbone architectures. We draw a series of intriguing observations from this study, e.g., we discover that encouraging long-spanned persistency can be effective even if the timespan is 60 seconds. In addition to state-of-the-art results in multiple benchmarks, we report a few promising cases in which unsupervised pre-training can outperform its supervised counterpart. Code will be made available at https://github.com/facebookresearch/SlowFast.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feichtenhofer_2021_CVPR, author = {Feichtenhofer, Christoph and Fan, Haoqi and Xiong, Bo and Girshick, Ross and He, Kaiming}, title = {A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {3299-3309} }