Intra-Class Amplitude Mixup for Data Augmentation in Image Classification

Mixup-based data augmentation improves deep neural network performance by enhancing training diversity, while amplitude mixing further enriches image style variations, benefiting tasks such as domain adaptation. However, the random selection of images for mixing in current amplitude-mixing approaches may introduce class-irrelevant information, potentially reducing their effectiveness in image classification. To address this, we propose Intra-Class Amplitude Mixup (ICAMix), a plug-and-play data augmentation method. To prevent random amplitude information from disrupting discriminative features in the mixed images, we restrict the mixing process to intra-class images, thereby enhancing the class discriminability of the generated images, making them more effective for classification tasks. Furthermore, since amplitude mixing preserves the structural integrity of images, our method effectively integrates multiple intra-class images, further enriching the diversity of features in the mixed images. Extensive experiments across various image classification tasks demonstrate that our method outperforms several baselines with minimal computational overheads. Visualizations of the generated images further validate its effectiveness. Our code is available at: https://github.com/rqfzpy/ICAMix.