用扩散模型生成蛋白图像，提升细胞定位分类效果
Leveraging Diffusion Models for Synthetic Data Augmentation in Protein Subcellular Localization Classification
- 用简化版条件扩散模型生成带标签的一致图像
- 混合训练策略使验证集表现提升，但测试集泛化差
- 真实数据+传统损失函数更稳定，适合生物医学图像分类
我们研究了利用扩散模型生成的合成图像是否能提升蛋白质亚细胞定位的多标签分类性能。具体地，我们实现了一个简化的类条件去噪扩散概率模型（DDPM），用于生成与标签一致的样本，并通过两种混合训练策略——混合损失和混合表示——将合成数据与真实数据结合。尽管这些方法在验证集上表现出色，但所提出的MixModel在未见测试数据上的泛化能力较差，凸显了有效利用合成数据的挑战。相比之下，基于ResNet主干网络和传统损失函数的基线分类器展现出更高的稳定性与测试性能。研究结果强调了在生物医学图像分类中引入生成式增强时，真实数据生成与稳健监督的重要性。
原文摘要 · Abstract (English)
We investigate whether synthetic images generated by diffusion models can enhance multi-label classification of protein subcellular localization. Specifically, we implement a simplified class-conditional denoising diffusion probabilistic model (DDPM) to produce label-consistent samples and explore their integration with real data via two hybrid training strategies: Mix Loss and Mix Representation. While these approaches yield promising validation performance, our proposed MixModel exhibits poor generalization to unseen test data, underscoring the challenges of leveraging synthetic data effectively. In contrast, baseline classifiers built on ResNet backbones with conventional loss functions demonstrate greater stability and test-time performance. Our findings highlight the importance of realistic data generation and robust supervision when incorporating generative augmentation into biomedical image classification.
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。