GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps

TL;DR

GuidedMixup is an efficient saliency-aware data augmentation method that improves image classification robustness by intelligently combining images based on saliency maps with low computational cost.

Contribution

It introduces a novel, low-overhead pairing algorithm and pixel-wise mixup ratio control to better preserve salient regions during augmentation.

Findings

Achieves a good balance between augmentation efficiency and classification performance.

Improves robustness on corrupted or reduced datasets.

Outperforms existing mixup strategies in experiments.

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.