Data-Efficient Instance Generation from Instance Discrimination

By Ceyuan Yang, Yujun Shen, Yinghao Xu, Bolei Zhou. 2021

97 citations recorded by the source corpus.

Generative Adversarial Networks (GANs) have significantly advanced image synthesis, however, the synthesis quality drops significantly given a limited amount of training data. To improve the data efficiency of GAN training, prior work typically employs data augmentation to mitigate the overfitting of the discriminator yet still learn the discriminator with a bi-classification (i.e., real vs. fake) task. In this work, we propose a data-efficient Instance Generation (InsGen) method based on instance discrimination. Concretely, besides differentiating the real domain from the fake domain, the discriminator is required to distinguish every individual image, no matter it comes from the training set or from the generator. In this way, the discriminator can benefit from the infinite synthesized samples for training, alleviating the overfitting problem caused by insufficient training data. A noise perturbation strategy is further introduced to improve its discriminative power. Meanwhile, the learned instance discrimination capability from the discriminator is in turn exploited to encourage the generator for diverse generation. Extensive experiments demonstrate the effectiveness of our method on a variety of datasets and training settings. Noticeably, on the setting of 2K training images from the FFHQ dataset, we outperform the state-of-the-art approach with 23.5% FID improvement.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Weizhu Chen
2. Pengcheng He
3. Bolei Zhou
4. Yujun Shen
5. Gal Chechik
6. Ceyuan Yang
7. Yinghao Xu
8. Jiapeng Zhu

In Computer Vision and Pattern Recognition

1. Daniel Cohen-Or
2. Luc Van Gool
3. Eli Shechtman
4. Or Patashnik
5. Amit H. Bermano
6. Bolei Zhou
7. Ming-Hsuan Yang
8. Rinon Gal

In Representation & Self-Supervised Learning

1. Yujun Shen
2. Bolei Zhou
3. Ceyuan Yang
4. Yinghao Xu
5. Rinon Gal
6. Daniel Cohen-Or
7. Gal Chechik
8. Amit H. Bermano

Citations in the corpus

• StyleGAN-NADA (2021, background): “Such works typically employ data augmentations [14, 41, 52, 53] or empower the discriminator to better learn from existing data using auxiliary tasks [23, 49].”
• One-Shot Generative Domain Adaptation (2021, background): “Under such a case, however, we manage to reuse the prior knowledge to the most extent ( i.e. , only training one layer in the generator and the discriminator each), and confirm that such an efficient scheme indeed facilitates generative domain adaptation and substantially outperforms existing…”
• Score Matching Model for Unbounded Data Score (2021, unknown): “54 Likelihood-free Models InsGen [52] 3.”
• Diffusion-GAN: Training GANs with Diffusion (2022, methodology): “Motivated by the success of InsGen (Yang et al., 2021) on small datasets, we build our Diffusion-GAN upon it.”