A recent work from Bello shows that training and scaling strategies may be more significant than model architectures for visual recognition. This short note studies effective training and scaling strategies for video recognition models. We propose a simple scaling strategy for 3D ResNets, in combination with improved training strategies and minor architectural changes. The resulting models, termed 3D ResNet-RS, attain competitive performance of 81.0 on Kinetics-400 and 83.8 on Kinetics-600 without pre-training. When pre-trained on a large Web Video Text dataset, our best model achieves 83.5 and 84.3 on Kinetics-400 and Kinetics-600. The proposed scaling rule is further evaluated in a self-supervised setup using contrastive learning, demonstrating improved performance. Code is available at: https://github.com/tensorflow/models/tree/master/official.
@article{arxiv.2109.01696,
title = {Revisiting 3D ResNets for Video Recognition},
author = {Xianzhi Du and Yeqing Li and Yin Cui and Rui Qian and Jing Li and Irwan Bello},
journal= {arXiv preprint arXiv:2109.01696},
year = {2021}
}