Regularization on Spatio-Temporally Smoothed Feature for Action Recognition

Jinhyung Kim, Seunghwan Cha, Dongyoon Wee, Soonmin Bae, Junmo Kim; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12103-12112

Abstract


Deep neural networks for video action recognition frequently require 3D convolutional filters and often encounter overfitting due to a larger number of parameters. In this paper, we propose Random Mean Scaling (RMS), a simple and effective regularization method, to relieve the overfitting problem in 3D residual networks. The key idea of RMS is to randomly vary the magnitude of low-frequency components of the feature to regularize the model. The low-frequency component can be derived by a spatio-temporal mean on the local patch of a feature. We present that selective regularization on this locally smoothed feature makes a model handle the low-frequency and high-frequency component distinctively, resulting in performance improvement. RMS can enhance a model with little additional computation only during training, similar to other regularization methods. RMS also can be incorporated into typical training process without any bells and whistles. Experimental results show the improvement in generalization performance on a popular action recognition datasets demonstrating the effectiveness of RMS as a regularization technique, compared to other state-of-the-art regularization methods.

Related Material


[pdf] [supp] [video]
[bibtex]
@InProceedings{Kim_2020_CVPR,
author = {Kim, Jinhyung and Cha, Seunghwan and Wee, Dongyoon and Bae, Soonmin and Kim, Junmo},
title = {Regularization on Spatio-Temporally Smoothed Feature for Action Recognition},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}