基于对比学习的多阶段渐进式微调SNN与基于RL的外部优化增强GANs的性能
Enhancing GANs with Contrastive Learning-Based Multistage Progressive Finetuning SNN and RL-Based External Optimization
AI总结：
针对GAN在高分辨率组织病理学图像合成中训练不稳定、模式崩溃等问题，提出融合对比学习多阶段渐进微调SNN与强化学习外部优化器的框架，多项指标优于SOTA模型。
摘要：
生成对抗网络（GANs）一直处于图像合成领域的前沿，尤其在组织病理学等医学领域，可帮助解决数据稀缺、患者隐私和类别不平衡等挑战。然而，若干固有问题及领域特定问题仍然存在。对GANs而言，训练不稳定、模式崩溃以及二分类反馈不足会削弱其性能。这些挑战在高分辨率组织病理学图像中尤为突出，因为这类图像特征表示复杂、空间细节丰富。针对这些挑战，本研究提出一种新型框架，将基于对比学习的多阶段渐进式微调孪生神经网络（MFT-SNN）与基于强化学习的外部优化器（RL-EO）相结合。MFT-SNN改进了组织病理学数据中的特征相似性提取，而RL-EO作为基于奖励的引导机制平衡GAN训练，解决模式崩溃问题并提升输出质量。该方法与当前最优（SOTA）GAN模型进行了对比评估，在多项指标上展现出更优性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
