Paper Info
Title
The Effects Of Regularization On Learning Facial Expressions With Convolutional Neural Networks
Abstract
Convolutional neural networks (CNNs) have become effective instruments in facial expression recognition. Very good results can be achieved with deep CNNs possessing many layers and providing a good internal representation of the learned data. Due to the potentially high complexity of CNNs on the other hand they are prone to overfitting and as a result, regularization techniques are needed to improve the performance and minimize overfitting. However, it is not yet clear how these regularization techniques affect the learned representation of faces. In this paper we examine the effects of novel regularization techniques on the training and performance of CNNs and their learned features. We train a CNN using dropout, max pooling dropout, batch normalization and different combinations of these three. We show that a combination of these methods can have a big impact on the performance of a CNN, almost halving its validation error. A visualization technique is applied to the CNNs to highlight their activations for different inputs, illustrating a significant difference between a standard CNN and a regularized CNN.
Year
DOI
Venue
2016
10.1007/978-3-319-44781-0_10
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II
Keywords
Field
DocType
Convolutional neural network, Facial expression recognition, Regularization, Batch normalization, Dropout, Max pooling dropout
Normalization (statistics),Pattern recognition,Visualization,Convolutional neural network,Computer science,Pooling,Facial expression,Regularization (mathematics),Artificial intelligence,Overfitting,Deep learning,Machine learning
Conference
Volume
ISSN
Citations 
9887
0302-9743
1
PageRank 
References 
Authors
0.35
8
3
Name
Order
Citations
PageRank
Tobias Hinz117730.11
Pablo V. A. Barros211922.02
Stefan Wermter31100151.62