research
∙
12/02/2021
Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency
Image resolution that has close relations with accuracy and computationa...
share
research
∙
07/18/2021
Feature Mining: A Novel Training Strategy for Convolutional Neural Network
In this paper, we propose a novel training strategy for convolutional ne...
research
∙
06/12/2021
Go Small and Similar: A Simple Output Decay Brings Better Performance
Regularization and data augmentation methods have been widely used and b...
research
∙
06/08/2021
White Paper Assistance: A Step Forward Beyond the Shortcut Learning
The promising performances of CNNs often overshadow the need to examine ...
research
∙
03/29/2021
FocusedDropout for Convolutional Neural Network
In convolutional neural network (CNN), dropout cannot work well because ...
research
∙
03/29/2021
Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions
In this paper, we propose Selective Output Smoothing Regularization, a n...
research
∙
03/09/2021