DJMix: Unsupervised Task-agnostic Image Augmentation for Improving Robustness of Convolutional Neural Networks

Ryuichiro Hataya, Hideki Nakayama

Abstract: Convolutional Neural Networks (CNNs) are vulnerable to unseen test-time noise on input images, such as defocus blur or JPEG-compression artifacts. Improving the robustness to such noise is important for real-world applications. In this paper, we propose DJMix, a training method for CNNs to obtain identical representations to a given image and its discretized one. As a result, CNNs trained with DJMix can ignore unnecessary details of inputs and become robust to input noise. We verify the effectiveness of our method on several datasets of various tasks, namely, classification, semantic segmentation, and object detection using clean and noisy test images.