TransformMix: Learning Transformation and Mixing Strategies from Data

arXiv:2403.12429v1 Announce Type: cross
Abstract: Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent sample-mixing methods, like Mixup and Cutmix, adopt simple mixing operations to blend multiple inputs. Although such a heuristic approach shows certain performance gains in some computer vision tasks, it mixes the images blindly and does not adapt to different datasets automatically. A mixing strategy …

abstract arxiv augmentation blend cs.cv cs.lg data deep learning inputs multiple operations popular power sample samples simple strategies training transformation type