用对比学习与强化学习改进生成对抗网络，提升病理图像生成质量。
Enhancing GANs with Contrastive Learning-Based Multistage Progressive Finetuning SNN and RL-Based External Optimization
- 分阶段渐进式孪生网络增强病理图像特征相似性提取
- 强化学习外部优化器缓解模式崩溃，提升生成图像多样性
- 专为高分辨率病理图像设计，适合医学图像生成场景
生成对抗网络（GAN）在图像合成中处于前沿地位，尤其在组织病理学等医疗领域，能应对数据稀缺、患者隐私和类别不平衡等问题。然而，训练不稳定性、模式崩溃以及二分类反馈不足等固有缺陷仍制约性能，尤其在高分辨率病理图像上表现更显著，因其特征复杂且空间细节丰富。为此，本文提出一种新框架，融合基于对比学习的多阶段渐进微调孪生神经网络（MFT-SNN）与基于强化学习的外部优化器（RL-EO）。MFT-SNN提升病理数据中的特征相似性捕捉能力，而RL-EO作为基于奖励的引导机制，平衡GAN训练过程，缓解模式崩溃并提高输出质量。所提方法在多个指标上优于现有最先进（SOTA）GAN模型。
原文摘要 · Abstract (English)
Generative Adversarial Networks (GANs) have been at the forefront of image synthesis, especially in medical fields like histopathology, where they help address challenges such as data scarcity, patient privacy, and class imbalance. However, several inherent and domain-specific issues remain. For GANs, training instability, mode collapse, and insufficient feedback from binary classification can undermine performance. These challenges are particularly pronounced with high-resolution histopathology images due to their complex feature representation and high spatial detail. In response to these challenges, this work proposes a novel framework integrating a contrastive learning-based Multistage Progressive Finetuning Siamese Neural Network (MFT-SNN) with a Reinforcement Learning-based External Optimizer (RL-EO). The MFT-SNN improves feature similarity extraction in histopathology data, while the RL-EO acts as a reward-based guide to balance GAN training, addressing mode collapse and enhancing output quality. The proposed approach is evaluated against state-of-the-art (SOTA) GAN models and demonstrates superior performance across multiple metrics.
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。