Timezone: »
The performance of generative adversarial networks (GANs) heavily deteriorates given a limited amount of training data. This is mainly because the discriminatorsis memorizing the exact training set. To combat it, we propose Differentiable Augmentation (DiffAugment), a simple method that improves the data efficiency of GANs by imposing various types of differentiable augmentations on both real and fake samples. Previous attempts to directly augment the training data manipulate the distribution of real images, yielding little benefit; DiffAugment enables us to adopt the differentiable augmentation for the generated samples, effectively stabilizes training, and leads to better convergence. Experiments demonstrate consistent gains of our method over a variety of GAN architectures and loss functions for both unconditional and class-conditional generation. With DiffAugment, we achieve astate-of-the-art FID of 6.80 with an IS of 100.8 on ImageNet 128×128 and 2-4× reductions of FID given 1,000 images on FFHQ and LSUN. Furthermore, with only 20% training data, we can match the top performance on CIFAR-10 and CIFAR-100. Finally, our method can generate high-fidelity images using only 100 images without pre-training, while being on par with existing transfer learning algorithms. Code is available at https://github.com/mit-han-lab/data-efficient-gans.
Author Information
Shengyu Zhao (Tsinghua University)
Zhijian Liu (MIT)
Ji Lin (MIT)
Jun-Yan Zhu (MIT)
Song Han (MIT)
More from the Same Authors
-
2020 Poster: MCUNet: Tiny Deep Learning on IoT Devices »
Ji Lin · Wei-Ming Chen · Yujun Lin · john cohn · Chuang Gan · Song Han -
2020 Spotlight: MCUNet: Tiny Deep Learning on IoT Devices »
Ji Lin · Wei-Ming Chen · Yujun Lin · john cohn · Chuang Gan · Song Han -
2020 Poster: TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning »
Han Cai · Chuang Gan · Ligeng Zhu · Song Han -
2019 Poster: Park: An Open Platform for Learning-Augmented Computer Systems »
Hongzi Mao · Parimarjan Negi · Akshay Narayan · Hanrui Wang · Jiacheng Yang · Haonan Wang · Ryan Marcus · Ravichandra Addanki · Mehrdad Khani Shirkoohi · Songtao He · Vikram Nathan · Frank Cangialosi · Shaileshh Venkatakrishnan · Wei-Hung Weng · Song Han · Tim Kraska · Dr.Mohammad Alizadeh -
2019 Poster: Deep Leakage from Gradients »
Ligeng Zhu · Zhijian Liu · Song Han -
2019 Poster: Point-Voxel CNN for Efficient 3D Deep Learning »
Zhijian Liu · Haotian Tang · Yujun Lin · Song Han -
2019 Spotlight: Point-Voxel CNN for Efficient 3D Deep Learning »
Zhijian Liu · Haotian Tang · Yujun Lin · Song Han -
2018 Poster: Visual Object Networks: Image Generation with Disentangled 3D Representations »
Jun-Yan Zhu · Zhoutong Zhang · Chengkai Zhang · Jiajun Wu · Antonio Torralba · Josh Tenenbaum · Bill Freeman -
2018 Poster: Learning to Exploit Stability for 3D Scene Parsing »
Yilun Du · Zhijian Liu · Hector Basevi · Ales Leonardis · Bill Freeman · Josh Tenenbaum · Jiajun Wu -
2018 Poster: 3D-Aware Scene Manipulation via Inverse Graphics »
Shunyu Yao · Tzu Ming Hsu · Jun-Yan Zhu · Jiajun Wu · Antonio Torralba · Bill Freeman · Josh Tenenbaum -
2018 Poster: Video-to-Video Synthesis »
Ting-Chun Wang · Ming-Yu Liu · Jun-Yan Zhu · Guilin Liu · Andrew Tao · Jan Kautz · Bryan Catanzaro