用特征核度量训练GAN，解决模式崩溃并自动选核函数。
CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metrics
- 基于特征核积分概率度量构建新GAN框架
- 在真实图像数据集上优于其他MMD-GAN，性能接近人工调优核
- 自动选择核函数，省去手动调参，适合想简化训练的开发者
本文提出CKGAN，一种基于特征核积分概率度量（CKIPM）的新型生成对抗网络。CKIPM通过优化再生核希尔伯特空间中最大均值差异（MMD）的下界，作为两个概率分布间的距离，用于训练GAN。CKGAN通过将生成图像映射回随机噪声来缓解模式崩溃问题。为避免手动选择核函数的繁琐，提出软选择方法自动学习特征核函数。在多个合成与真实图像基准数据集（如MNIST、CelebA）上的实验表明，CKGAN普遍优于其他基于MMD的GAN。结果还显示，虽训练时间略有增加，但自动选择的核函数在真实图像数据集上表现接近人工精细调优的最佳核，且能提升其他MMD-GAN的性能。
原文摘要 · Abstract (English)
In this paper, we propose CKGAN, a novel generative adversarial network (GAN) variant based on an integral probability metrics framework with characteristic kernel (CKIPM). CKIPM, as a distance between two probability distributions, is designed to optimize the lowerbound of the maximum mean discrepancy (MMD) in a reproducing kernel Hilbert space, and thus can be used to train GANs. CKGAN mitigates the notorious problem of mode collapse by mapping the generated images back to random noise. To save the effort of selecting the kernel function manually, we propose a soft selection method to automatically learn a characteristic kernel function. The experimental evaluation conducted on a set of synthetic and real image benchmarks (MNIST, CelebA, etc.) demonstrates that CKGAN generally outperforms other MMD-based GANs. The results also show that at the cost of moderately more training time, the automatically selected kernel function delivers very close performance to the best of manually fine-tuned one on real image benchmarks and is able to improve the performances of other MMD-based GANs.
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。