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.
@article{arxiv.2210.04889,
title = {Turbo Training with Token Dropout},
author = {Tengda Han and Weidi Xie and Andrew Zisserman},
journal= {arXiv preprint arXiv:2210.04889},
year = {2022}
}