Minsoo, Kang Kim, Suhyun 2024-01-12T02:47:28Z 2024-01-12T02:47:28Z 2023-11-26 2023-02 https://pubs.kist.re.kr/handle/201004/76499 https://underline.io/events/380/sessions/14416/lecture/68539-guidedmixup-an-efficient-mixup-strategy-guided-by-saliency-maps 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. English ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps Conference 1 37th AAAI Conference on Artificial Intelligence (AAAI) / 35th Conference on Innovative Applications of Artificial Intelligence / 13th Symposium on Educational Advances in Artificial Intelligence, pp.1096 - 1104 37th AAAI Conference on Artificial Intelligence (AAAI) / 35th Conference on Innovative Applications of Artificial Intelligence / 13th Symposium on Educational Advances in Artificial Intelligence 1096 1104 US Washington, DC, USA 2023-02-07 THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 1 001243759700122