Large Scale Adversarial Representation Learning
Jeff Donahue DeepMind、Karen Simonyan DeepMind
Abstract
Adversarially trained generative models (GANs) have recently achieved compelling image synthesis results. But despite early successes in using GANs for unsupervised representation learning, they have since been superseded by approaches based on self-supervision. In this work we show that progress in image generation quality translates to substantially improved representation learning performance. Our approach, BigBiGAN, builds upon the state-of-the-art BigGAN model, extending it to representation learning by adding an encoder and modifying the discriminator. We extensively evaluate the representation learning and generation capabilities of these BigBiGAN models, demonstrating that these generation-based models achieve the state of the art in unsupervised representation learning on ImageNet, as well as in unconditional image generation. Pretrained BigBiGAN models – including image generators and encoders – are available on TensorFlow Hub111 Models available at https://tfhub.dev/s?publisher=deepmind&q=bigbigan, with a Colab notebook demo at https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/bigbigan_with_tf_hub.ipynb..
中文速览
生成式对抗网络（GAN）理论上应该能学到丰富的视觉语义，却长期在无监督表征学习上输给自监督方法——这项工作正是要填补这个差距。研究者在当时最强的图像生成模型 BigGAN 基础上，加入一个编码器（encoder）并改进判别器，构建出 BigBiGAN 模型，让生成器和编码器互为逆映射，迫使模型在生成高质量图像的同时学到有意义的图像表征。在 ImageNet 上的评测表明，BigBiGAN 不仅在无监督表征学习的线性分类指标上达到当时最优水平，还在无条件图像生成质量上超越了此前的同类方法。这项工作的意义在于，它首次清晰地证明了生成模型的进步可以直接转化为更好的表征学习能力，让"通过生成来理解数据"这一长期愿景向现实迈进了一大步。
原文 arXiv:1907.02544;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1907.02544v2