Revisiting 3D ResNets for Video Recognition

3 Sep 2021  ·  Xianzhi Du, Yeqing Li, Yin Cui, Rui Qian, Jing Li, Irwan Bello ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Classification Kinetics-400 R3D-RS-200 Acc@1 80.4 # 95
Acc@5 94.4 # 70
Action Classification Kinetics-600 R3D-RS-200 Top-1 Accuracy 83.1 # 40

Methods