{"ID":2892243,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15577","arxiv_id":"2507.15577","title":"GeMix: Conditional GAN-Based Mixup for Improved Medical Image Augmentation","abstract":"Mixup has become a popular augmentation strategy for image classification, yet its naive pixel-wise interpolation often produces unrealistic images that can hinder learning, particularly in high-stakes medical applications. We propose GeMix, a two-stage framework that replaces heuristic blending with a learned, label-aware interpolation powered by class-conditional GANs. First, a StyleGAN2-ADA generator is trained on the target dataset. During augmentation, we sample two label vectors from Dirichlet priors biased toward different classes and blend them via a Beta-distributed coefficient. Then, we condition the generator on this soft label to synthesize visually coherent images that lie along a continuous class manifold. We benchmark GeMix on the large-scale COVIDx-CT-3 dataset using three backbones (ResNet-50, ResNet-101, EfficientNet-B0). When combined with real data, our method increases macro-F1 over traditional mixup for all backbones, reducing the false negative rate for COVID-19 detection. GeMix is thus a drop-in replacement for pixel-space mixup, delivering stronger regularization and greater semantic fidelity, without disrupting existing training pipelines. We publicly release our code at https://github.com/hugocarlesso/GeMix to foster reproducibility and further research.","short_abstract":"Mixup has become a popular augmentation strategy for image classification, yet its naive pixel-wise interpolation often produces unrealistic images that can hinder learning, particularly in high-stakes medical applications. We propose GeMix, a two-stage framework that replaces heuristic blending with a learned, label-a...","url_abs":"https://arxiv.org/abs/2507.15577","url_pdf":"https://arxiv.org/pdf/2507.15577v2","authors":"[\"Hugo Carlesso\",\"Maria Eliza Patulea\",\"Moncef Garouani\",\"Radu Tudor Ionescu\",\"Josiane Mothe\"]","published":"2025-07-21T12:58:05Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":611975,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2892243,"paper_url":"https://arxiv.org/abs/2507.15577","paper_title":"GeMix: Conditional GAN-Based Mixup for Improved Medical Image Augmentation","repo_url":"https://github.com/hugocarlesso/GeMix","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}