Improving Image Classification Accuracy through Complementary Intra-Class and Inter-Class Mixup

arXiv:2403.14137v1 Announce Type: cross
Abstract: MixUp and its variants, such as Manifold MixUp, have two key limitations in image classification tasks. First, they often neglect mixing within the same class (intra-class mixup), leading to an underutilization of the relationships among samples within the same class. Second, although these methods effectively enhance inter-class separability by mixing between different classes (inter-class mixup), they fall short in improving intra-class cohesion through their mixing operations, limiting their classification performance. To tackle these issues, we …

abstract accuracy arxiv class classification cs.cv cs.lg image improving key limitations manifold relationships samples tasks through type variants