论文标题
contragan：有条件图像产生的对比度学习
ContraGAN: Contrastive Learning for Conditional Image Generation
论文作者
论文摘要
有条件的图像生成是使用类标签信息生成不同图像的任务。尽管许多条件生成的对抗网络（GAN）已经显示出现实的结果，但这种方法将图像嵌入与相应标签（数据对类关系）的嵌入之间的成对关系视为条件损失。在本文中，我们提出了contragan，该contravan考虑了通过使用条件对比损失，考虑了同一批次（数据之间关系）中多个图像嵌入之间的关系以及数据对类关系。 contragan的歧视者歧视给定样品的真实性，并最大程度地减少了学习训练图像之间关系的对比目标。同时，发电机试图生成欺骗真实性并具有低对比度损失的逼真的图像。实验结果表明，在小型图像网和Imagenet数据集上，Contragan的表现分别优于最先进的模型和7.7％。此外，我们在实验上证明了对比学习有助于缓解歧视者的过度拟合。为了进行公平的比较，我们使用Pytorch库重新实现了十二个最先进的甘斯。该软件包可在https://github.com/postech-cvlab/pytorch-studiogan上找到。
Conditional image generation is the task of generating diverse images using class label information. Although many conditional Generative Adversarial Networks (GAN) have shown realistic results, such methods consider pairwise relations between the embedding of an image and the embedding of the corresponding label (data-to-class relations) as the conditioning losses. In this paper, we propose ContraGAN that considers relations between multiple image embeddings in the same batch (data-to-data relations) as well as the data-to-class relations by using a conditional contrastive loss. The discriminator of ContraGAN discriminates the authenticity of given samples and minimizes a contrastive objective to learn the relations between training images. Simultaneously, the generator tries to generate realistic images that deceive the authenticity and have a low contrastive loss. The experimental results show that ContraGAN outperforms state-of-the-art-models by 7.3% and 7.7% on Tiny ImageNet and ImageNet datasets, respectively. Besides, we experimentally demonstrate that contrastive learning helps to relieve the overfitting of the discriminator. For a fair comparison, we re-implement twelve state-of-the-art GANs using the PyTorch library. The software package is available at https://github.com/POSTECH-CVLab/PyTorch-StudioGAN.
