Regularization on Spatio-Temporally Smoothed Feature for Action Recognition
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionTemporal Action LocalizationSimilar Papers 제목 키워드 기반
VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation
Vision-language-action (VLA) models show potential for general robotic tasks, but remain challenging in spatiotemporally coherent manipulation, which requires fine-grained representations. Typically, existing methods emb…
A Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions
Spatio-temporal action detection is an important and challenging problem in video understanding. However, the application of the existing large-scale spatio-temporal action datasets in specific fields is limited, and the…
Action DetectionVideo UnderstandingSTAIC regularization for spatio-temporal image reconstruction
We propose a regularization-based image restoration scheme for 2D images recorded over time (2D+t). We design an infimal convolution-based regularization function which we call spatio-temporal Adaptive Infimal Convolutio…
FormImage ReconstructionImage RestorationWasserstein total variation filtering
In this paper, we expand upon the theory of trend filtering by introducing the use of the Wasserstein metric as a means to control the amount of spatiotemporal variation in filtered time series data. While trend filterin…
Time SeriesTime Series AnalysisSelf-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition
Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data. Different from existing w…
Action RecognitionData AugmentationSelf-Supervised Learning