GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps
This work addresses the problem of high computational costs in data augmentation for image classification, offering an incremental improvement over existing mixup strategies.
The paper tackles the computational burden of saliency-aware mixup methods by proposing GuidedMixup, an efficient pairing algorithm that minimizes conflict between salient regions and controls pixel-wise mixup ratios, achieving a good trade-off between augmentation overhead and generalization performance on classification datasets.
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.