DropFilter: Dropout for Convolutions
This work addresses overfitting in convolutional layers for computer vision tasks, offering a domain-specific improvement.
The authors tackled the problem of overfitting in convolutional neural networks by proposing DropFilter, a dropout method that randomly suppresses filter outputs, which improved performance on CIFAR and ImageNet datasets.
Using a large number of parameters , deep neural networks have achieved remarkable performance on computer vison and natural language processing tasks. However the networks usually suffer from overfitting by using too much parameters. Dropout is a widely use method to deal with overfitting. Although dropout can significantly regularize densely connected layers in neural networks, it leads to suboptimal results when using for convolutional layers. To track this problem, we propose DropFilter, a new dropout method for convolutional layers. DropFilter randomly suppresses the outputs of some filters. Because it is observed that co-adaptions are more likely to occurs inter filters rather than intra filters in convolutional layers. Using DropFilter, we remarkably improve the performance of convolutional networks on CIFAR and ImageNet.