DJMix: Unsupervised Task-agnostic Augmentation for Improving Robustness

Ryuichiro Hataya, Hideki Nakayama

Keywords: robustness, uncertainty, discretization, data augmentation

Abstract: Convolutional Neural Networks (CNNs) are vulnerable to unseen noise on input images at the test time, and thus improving the robustness is crucial. In this paper, we propose DJMix, a data augmentation method to improve the robustness by mixing each training image and its discretized one. Discretization is done in an unsupervised manner by an autoencoder, and the mixed images are nearly impossible to distinguish from the original images. Therefore, DJMix can easily be adapted to various image recognition tasks. We verify the effectiveness of our method using classification, semantic segmentation, and detection using clean and noisy test images.

One-sentence Summary: We propose a task-agnostic data augmentation method to make CNN models robust to test-time noise on images

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=s2L2dHjJA6