论文标题
Studiogan：图像合成的gans的分类学和基准
StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis
论文作者
论文摘要
生成对抗网络（GAN）是现实图像合成的最新生成模型之一。虽然培训和评估GAN变得越来越重要，但当前的GAN研究生态系统并未提供可靠的基准测试，以始终如一地进行评估。此外，由于GAN实施很少，因此研究人员将大量时间用于重现基线。我们研究了GAN方法的分类学，并提出了一个名为Studiogan的新开源库。 Studiogan支持7种GAN架构，9种调理方法，4种对抗损失，12个正则化模块，3个可区分的增强，7个评估指标和5个评估骨干。通过我们的培训和评估协议，我们使用各种数据集（CIFAR10，Imagenet，afhqv2，FFHQ和Baby/Papa/Granpa-Immagenet）和3个不同的评估骨干（InceptionV3，Swav，Swav和Swin Transformer）提出了大规模的基准。与GAN社区中使用的其他基准不同，我们在统一的培训管道中培训了代表GAN，包括Biggan和Stylegan系列，并使用7个评估指标量化了发电性能。基准测试评估其他尖端生成模型（例如，stylegan-xl，adm，maskgit和rq-transformer）。 Studiogan提供了预先训练的权重的GAN实现，培训和评估脚本。 Studiogan可从https://github.com/postech-cvlab/pytorch-studiogan获得。
Generative Adversarial Network (GAN) is one of the state-of-the-art generative models for realistic image synthesis. While training and evaluating GAN becomes increasingly important, the current GAN research ecosystem does not provide reliable benchmarks for which the evaluation is conducted consistently and fairly. Furthermore, because there are few validated GAN implementations, researchers devote considerable time to reproducing baselines. We study the taxonomy of GAN approaches and present a new open-source library named StudioGAN. StudioGAN supports 7 GAN architectures, 9 conditioning methods, 4 adversarial losses, 12 regularization modules, 3 differentiable augmentations, 7 evaluation metrics, and 5 evaluation backbones. With our training and evaluation protocol, we present a large-scale benchmark using various datasets (CIFAR10, ImageNet, AFHQv2, FFHQ, and Baby/Papa/Granpa-ImageNet) and 3 different evaluation backbones (InceptionV3, SwAV, and Swin Transformer). Unlike other benchmarks used in the GAN community, we train representative GANs, including BigGAN and StyleGAN series in a unified training pipeline and quantify generation performance with 7 evaluation metrics. The benchmark evaluates other cutting-edge generative models (e.g., StyleGAN-XL, ADM, MaskGIT, and RQ-Transformer). StudioGAN provides GAN implementations, training, and evaluation scripts with the pre-trained weights. StudioGAN is available at https://github.com/POSTECH-CVLab/PyTorch-StudioGAN.
