用条件生成对抗网络让医学图像混合法更真实，提升新冠检测准确率。
GeMix: Conditional GAN-Based Mixup for Improved Medical Image Augmentation
- 用条件GAN替代传统像素混合，生成更符合解剖结构的图像。
- 在COVIDx-CT-3数据集上，所有模型的宏平均F1均提升，假阴性率下降。
- 可直接替换现有训练流程，适合医疗图像增强研究者使用。
Mixup已成为图像分类中的流行增强策略，但其简单的像素插值常产生不真实的图像，尤其在高风险的医学应用中会阻碍学习。本文提出GeMix，一种两阶段框架，以类条件生成对抗网络实现学习过的、标签感知的插值。首先，在目标数据集上训练StyleGAN2-ADA生成器；增强时，从偏向不同类别的狄利克雷先验中采样两个标签向量，通过贝塔分布系数混合，并将该软标签作为条件输入生成器，合成沿连续类别流形分布的视觉一致图像。我们在大规模COVIDx-CT-3数据集上测试，采用三个主干网络（ResNet-50、ResNet-101、EfficientNet-B0）。结合真实数据后，所有主干模型的宏平均F1均高于传统mixup，显著降低新冠检测假阴性率。GeMix是像素空间mixup的即插即用替代方案，提供更强正则化与更高语义保真度，且不破坏现有训练流程。代码已公开于https://github.com/hugocarlesso/GeMix，促进可复现性与后续研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。