用铰链损失与RLC正则化，解决生成对抗网络模式崩溃问题
HingeRLC-GAN: Combating Mode Collapse with Hinge Loss and RLC Regularization
- 引入铰链损失和RLC正则化，提升生成多样性
- FID 18，KID 0.001，优于现有方法
- 适合关注生成质量与稳定性的研究人员
近年来，生成对抗网络（GAN）在生成高质量图像方面取得了显著进展。然而，模式崩溃问题依然存在，即生成器仅产出有限的几种数据模式，无法反映训练数据集的多样性。本研究通过一系列架构改进，旨在提升GAN模型的多样性和稳定性。首先，采用Wasserstein损失与梯度惩罚改进损失函数，以更好捕捉数据的全部变化范围。同时，实验对比多种网络结构，发现ResNet能显著提升多样性。基于上述发现，提出HingeRLC-GAN，结合RLC正则化与铰链损失函数。该方法在测试中取得FID分数18、KID分数0.001，有效平衡了训练稳定性和生成多样性，性能优于现有方法。
原文摘要 · Abstract (English)
Recent advances in Generative Adversarial Networks (GANs) have demonstrated their capability for producing high-quality images. However, a significant challenge remains mode collapse, which occurs when the generator produces a limited number of data patterns that do not reflect the diversity of the training dataset. This study addresses this issue by proposing a number of architectural changes aimed at increasing the diversity and stability of GAN models. We start by improving the loss function with Wasserstein loss and Gradient Penalty to better capture the full range of data variations. We also investigate various network architectures and conclude that ResNet significantly contributes to increased diversity. Building on these findings, we introduce HingeRLC-GAN, a novel approach that combines RLC Regularization and the Hinge loss function. With a FID Score of 18 and a KID Score of 0.001, our approach outperforms existing methods by effectively balancing training stability and increased diversity.
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。