Accelerating Self-Supervised Learning via Efficient Training Strategies
This work addresses the high computational cost and resource barriers in self-supervised learning, making it more accessible, though it is incremental as it builds on existing methods.
The paper tackled the problem of long training times in self-supervised learning for computer vision by proposing model-agnostic strategies, resulting in up to 2.7 times speed-up while maintaining comparable performance.
Recently the focus of the computer vision community has shifted from expensive supervised learning towards self-supervised learning of visual representations. While the performance gap between supervised and self-supervised has been narrowing, the time for training self-supervised deep networks remains an order of magnitude larger than its supervised counterparts, which hinders progress, imposes carbon cost, and limits societal benefits to institutions with substantial resources. Motivated by these issues, this paper investigates reducing the training time of recent self-supervised methods by various model-agnostic strategies that have not been used for this problem. In particular, we study three strategies: an extendable cyclic learning rate schedule, a matching progressive augmentation magnitude and image resolutions schedule, and a hard positive mining strategy based on augmentation difficulty. We show that all three methods combined lead up to 2.7 times speed-up in the training time of several self-supervised methods while retaining comparable performance to the standard self-supervised learning setting.