提出配对正则化，解决生成模型中多个输入映射到同一输出的问题。
Pairing Regularization for Mitigating Many-to-One Collapse in GANs
- 通过配对正则化约束潜在变量与生成样本的局部一致性。
- 在探索不足时提升覆盖率和召回率，在稳定训练时提高精度不降召回。
- 适合关注生成多样性与质量平衡的研究者或工程实践者。
模式崩溃仍是生成对抗网络（GAN）训练中的根本挑战。现有工作多聚焦于模式丢失等跨模式崩溃，而对同一模式内多个潜在变量映射到相同或高度相似输出的「多对一崩溃」关注较少。本文提出一种与生成器联合优化的配对正则化方法，通过强制潜在变量与生成样本间的局部一致性，缓解多对一崩溃。实验表明，该正则化效果取决于训练的主导失败模式：在探索受限的易崩溃阶段，可促进结构化局部探索，提升覆盖范围与召回率；在充分探索的稳定阶段，则通过抑制冗余映射，优化生成数据密度，提升精度而不损失召回率。在合成分布与真实图像基准上的大量实验验证了该方法能有效补充现有稳定技术，直接应对内模式崩溃问题。
原文摘要 · Abstract (English)
Mode collapse remains a fundamental challenge in training generative adversarial networks (GANs). While existing works have primarily focused on inter-mode collapse, such as mode dropping, intra-mode collapse-where many latent variables map to the same or highly similar outputs-has received significantly less attention. In this work, we propose a pairing regularizer jointly optimized with the generator to mitigate the many-to-one collapse by enforcing local consistency between latent variables and generated samples. We show that the effect of pairing regularization depends on the dominant failure mode of training. In collapse-prone regimes with limited exploration, pairing encourages structured local exploration, leading to improved coverage and higher recall. In contrast, under stabilized training with sufficient exploration, pairing refines the generator's induced data density by discouraging redundant mappings, thereby improving precision without sacrificing recall. Extensive experiments on both toy distributions and real-image benchmarks demonstrate that the proposed regularizer effectively complements existing stabilization techniques by directly addressing intra-mode collapse.
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。