Abstract
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because self-supervision requires no manual labels. In this work, we revisit this principle and scale two popular self-supervised approaches to 100 million images. We show that by scaling on various axes (including data size and problem 'hardness'), one can largely match or even exceed the performance of supervised pre-training on a variety of tasks such as object detection, surface normal estimation (3D) and visual navigation using reinforcement learning. Scaling these methods also provides many interesting insights into the limitations of current self-supervised techniques and evaluations. We conclude that current self-supervised methods are not 'hard' enough to take full advantage of large scale data and do not seem to learn effective high level semantic representations. We also introduce an extensive benchmark across 9 different datasets and tasks. We believe that such a benchmark along with comparable evaluation settings is necessary to make meaningful progress.
Abstract (translated)
自我监督学习的目的是在没有明确的人工监督的情况下，从数据本身学习表示。现有的工作忽略了自我监督学习的一个重要方面——扩展到大量数据的能力，因为自我监督不需要手动标签。在这项工作中，我们重新审视这一原则，并将两种流行的自我监督方法扩展到1亿幅图像。我们表明，通过在不同轴上缩放（包括数据大小和问题“硬度”），可以在很大程度上匹配甚至超过在各种任务（如目标检测、表面法向估计（3D）和使用强化学习的视觉导航）的监督预培训的性能。扩展这些方法还提供了许多有趣的洞察当前自我监督技术和评估的局限性。我们得出的结论是，当前的自监督方法不够“困难”，无法充分利用大规模数据，而且似乎无法学习有效的高级语义表示。我们还在9个不同的数据集和任务中引入了广泛的基准。我们认为，这样的基准以及可比较的评估设置对于取得有意义的进展是必要的。
URL
https://arxiv.org/abs/1905.01235
