DJMix: Unsupervised Task-agnostic Augmentation for Improving Robustness
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.
PDF Abstract
Datasets
CIFAR-10
CIFAR-100
ImageNet-C
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
No methods listed for this paper. Add
relevant methods here
