Improved Regularization of Convolutional Neural Networks with Cutout
This addresses the problem of overfitting in CNNs for computer vision tasks, offering an easy-to-implement method that improves generalization, though it is incremental as it builds on existing regularization approaches.
The paper tackles overfitting in convolutional neural networks by introducing cutout, a simple regularization technique that randomly masks square regions of input during training, achieving new state-of-the-art test errors of 2.56% on CIFAR-10, 15.20% on CIFAR-100, and 1.30% on SVHN.
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks. However, due to the model capacity required to capture such representations, they are often susceptible to overfitting and therefore require proper regularization in order to generalize well. In this paper, we show that the simple regularization technique of randomly masking out square regions of input during training, which we call cutout, can be used to improve the robustness and overall performance of convolutional neural networks. Not only is this method extremely easy to implement, but we also demonstrate that it can be used in conjunction with existing forms of data augmentation and other regularizers to further improve model performance. We evaluate this method by applying it to current state-of-the-art architectures on the CIFAR-10, CIFAR-100, and SVHN datasets, yielding new state-of-the-art results of 2.56%, 15.20%, and 1.30% test error respectively. Code is available at https://github.com/uoguelph-mlrg/Cutout