论文标题
多域图像到图像翻译的内容丰富的样品挖掘网络
Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
论文作者
论文摘要
在深层生成模型中，最近的进展可显着改善多域图像到图像翻译的性能。现有方法可以使用统一模型来实现所有视觉域之间的翻译。但是，当存在较大的域变化时，它们的结果远非令人满意。在本文中，我们揭示了改善样本选择策略是一个有效的解决方案。为了选择内容丰富的样本，我们在培训生成对抗网络期间动态估计样本的重要性，并提供信息丰富的样本挖掘网络。我们理论上分析了样本重要性与全局最佳歧视者的预测之间的关系。然后得出了对一般条件的实际重要性估计函数。此外，我们提出了一种新型的多阶段样本训练方案，以减少样品硬度，同时保留样本信息。进行了广泛的对特定图像到图像翻译任务的实验，结果证明了我们优于当前最新方法。
The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models. Existing approaches can use a unified model to achieve translations between all the visual domains. However, their outcomes are far from satisfying when there are large domain variations. In this paper, we reveal that improving the sample selection strategy is an effective solution. To select informative samples, we dynamically estimate sample importance during the training of Generative Adversarial Networks, presenting Informative Sample Mining Network. We theoretically analyze the relationship between the sample importance and the prediction of the global optimal discriminator. Then a practical importance estimation function for general conditions is derived. Furthermore, we propose a novel multi-stage sample training scheme to reduce sample hardness while preserving sample informativeness. Extensive experiments on a wide range of specific image-to-image translation tasks are conducted, and the results demonstrate our superiority over current state-of-the-art methods.
