论文标题
用令牌辍学的涡轮训练
Turbo Training with Token Dropout
论文作者
论文摘要
本文的目的是用于视频任务的有效培训方法。我们做出了三个贡献：（1）我们提出了Turbo Training，这是用于多个视频任务的变压器的简单而多功能的训练范式。 （2）我们说明了涡轮培训在动作分类，视频表示学习和长期活动的活动分类方面的优势，这表明涡轮训练可以在很大程度上保持竞争性能，同时实现近4倍的加速速度，并且记忆消耗少。 （3）Turbo培训可以使长期安排的视频语言培训和端到端的长时间视频培训，比以前的作品提供竞争性或卓越的性能，而这些作品是在有限的资源下训练而言是不可行的。
The objective of this paper is an efficient training method for video tasks. We make three contributions: (1) We propose Turbo training, a simple and versatile training paradigm for Transformers on multiple video tasks. (2) We illustrate the advantages of Turbo training on action classification, video-language representation learning, and long-video activity classification, showing that Turbo training can largely maintain competitive performance while achieving almost 4X speed-up and significantly less memory consumption. (3) Turbo training enables long-schedule video-language training and end-to-end long-video training, delivering competitive or superior performance than previous works, which were infeasible to train under limited resources.
