论文标题
BigDatasetgan：与像素的综合成像网
BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations
论文作者
论文摘要
用像素标签注释图像是一个耗时且昂贵的过程。最近，DataSetgan展示了一种有希望的替代方案 - 通过利用一组手动标记的，GAN生成的图像来通过生成对抗网络（GAN）合成大型标记的数据集。在这里，我们将数据集扩展到类多样性的ImageNet量表。我们从经过ImageNet训练的班级生成模型Biggan中获取图像样本，并为所有1K类手动注释每类5张图像。通过在Biggan上训练有效的功能分割体系结构，我们将Biggan变成了标签的数据集发电机。我们进一步表明，Vqgan可以类似地用作数据集生成器，利用已经注释的数据。我们通过标记一组8K真实图像并评估各种设置中的细分性能来创建新的Imagenet基准测试。通过一项广泛的消融研究，我们显示了利用大型生成的数据集在像素任务上训练不同监督和自我保护的骨干模型的巨大收益。此外，我们证明，使用合成的数据集进行预训练可导致对标准图像网的预训练的改进，例如Pascal-Voc，MS-Coco，MS-Coco，CityScapes和City X射线和胸部X射线，以及任务（检测，分割）。我们的基准将公开并为这项具有挑战性的任务维护排行榜。项目页面：https：//nv-tlabs.github.io/big-datasetgan/
Annotating images with pixel-wise labels is a time-consuming and costly process. Recently, DatasetGAN showcased a promising alternative - to synthesize a large labeled dataset via a generative adversarial network (GAN) by exploiting a small set of manually labeled, GAN-generated images. Here, we scale DatasetGAN to ImageNet scale of class diversity. We take image samples from the class-conditional generative model BigGAN trained on ImageNet, and manually annotate 5 images per class, for all 1k classes. By training an effective feature segmentation architecture on top of BigGAN, we turn BigGAN into a labeled dataset generator. We further show that VQGAN can similarly serve as a dataset generator, leveraging the already annotated data. We create a new ImageNet benchmark by labeling an additional set of 8k real images and evaluate segmentation performance in a variety of settings. Through an extensive ablation study we show big gains in leveraging a large generated dataset to train different supervised and self-supervised backbone models on pixel-wise tasks. Furthermore, we demonstrate that using our synthesized datasets for pre-training leads to improvements over standard ImageNet pre-training on several downstream datasets, such as PASCAL-VOC, MS-COCO, Cityscapes and chest X-ray, as well as tasks (detection, segmentation). Our benchmark will be made public and maintain a leaderboard for this challenging task. Project Page: https://nv-tlabs.github.io/big-datasetgan/
