GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps

Abstract

Data augmentation is now an essential part of the image training process, as it effectively prevents overfitting and makes the model more robust against noisy datasets. Recent mixing augmentation strategies have advanced to generate the mixup mask that can enrich the saliency information, which is a supervisory signal. However, these methods incur a significant computational burden to optimize the mixup mask. From this motivation, we propose a novel saliency-aware mixup method, GuidedMixup, which aims to retain the salient regions in mixup images with low computational overhead. We develop an efficient pairing algorithm that pursues to minimize the conflict of salient regions of paired images and achieve rich saliency in mixup images. Moreover, GuidedMixup controls the mixup ratio for each pixel to better preserve the salient region by interpolating two paired images smoothly. The experiments on several datasets demonstrate that GuidedMixup provides a good trade-off between augmentation overhead and generalization performance on classification datasets. In addition, our method shows good performance in experiments with corrupted or reduced datasets.

Published at AAAI2023 (Oral)

References in corpus (6)

• Improved Regularization of Convolutional Neural Networks with Cutout
• AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
• A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
• Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
• Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
• SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

Cited by in corpus (2)

• HSMix: Hard and Soft Mixing Data Augmentation for Medical Image Segmentation
• Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN