PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
This addresses the generalization issue in CNNs for computer vision tasks, but it is incremental as it builds on existing mixing-based regularization methods.
The paper tackles the problem of high generalization gap in large capacity deep learning models trained with limited labeled data by proposing PatchUp, a feature-space block-level regularization technique for CNNs, which improves or equals state-of-the-art performance on datasets like CIFAR10/100 and ImageNet, and enhances robustness to deformed samples and adversarial attacks.
Large capacity deep learning models are often prone to a high generalization gap when trained with a limited amount of labeled training data. A recent class of methods to address this problem uses various ways to construct a new training sample by mixing a pair (or more) of training samples. We propose PatchUp, a hidden state block-level regularization technique for Convolutional Neural Networks (CNNs), that is applied on selected contiguous blocks of feature maps from a random pair of samples. Our approach improves the robustness of CNN models against the manifold intrusion problem that may occur in other state-of-the-art mixing approaches. Moreover, since we are mixing the contiguous block of features in the hidden space, which has more dimensions than the input space, we obtain more diverse samples for training towards different dimensions. Our experiments on CIFAR10/100, SVHN, Tiny-ImageNet, and ImageNet using ResNet architectures including PreActResnet18/34, WRN-28-10, ResNet101/152 models show that PatchUp improves upon, or equals, the performance of current state-of-the-art regularizers for CNNs. We also show that PatchUp can provide a better generalization to deformed samples and is more robust against adversarial attacks.