Training Generative Adversarial Networks with Limited Data

• URL: http://arxiv.org/abs/2006.06676v2
• Date: Wed, 7 Oct 2020 17:09:24 GMT
• Title: Training Generative Adversarial Networks with Limited Data
• Authors: Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, Timo Aila
• Abstract summary: We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. Good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images.
• Score: 42.72100066471578
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.59 to 2.42.

Related papers

• Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs [9.010643838773477]
  We introduce a novel score for quantifying overfit, which monitors the forgetting rate of deep models on validation data. We show that overfit can occur with and without a decrease in validation accuracy, and may be more common than previously appreciated. We use our observations to construct a new ensemble method, based solely on the training history of a single network, which provides significant improvement without any additional cost in training time.
  arXiv  Detail & Related papers  (2023-10-17T09:22:22Z)
• The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes [3.7189423451031356]
  We propose a framework to improve generalization from small amounts of data. We augment modern CNNs with fully-connected layers and show the massive impact this architectural change has in low-data regimes.
  arXiv  Detail & Related papers  (2022-10-11T17:55:10Z)
• Multi-Domain Joint Training for Person Re-Identification [51.73921349603597]
  Deep learning-based person Re-IDentification (ReID) often requires a large amount of training data to achieve good performance. It appears that collecting more training data from diverse environments tends to improve the ReID performance. We propose an approach called Domain-Camera-Sample Dynamic network (DCSD) whose parameters can be adaptive to various factors.
  arXiv  Detail & Related papers  (2022-01-06T09:20:59Z)
• Class Balancing GAN with a Classifier in the Loop [58.29090045399214]
  We introduce a novel theoretically motivated Class Balancing regularizer for training GANs. Our regularizer makes use of the knowledge from a pre-trained classifier to ensure balanced learning of all the classes in the dataset. We demonstrate the utility of our regularizer in learning representations for long-tailed distributions via achieving better performance than existing approaches over multiple datasets.
  arXiv  Detail & Related papers  (2021-06-17T11:41:30Z)
• Regularizing Generative Adversarial Networks under Limited Data [88.57330330305535]
  This work proposes a regularization approach for training robust GAN models on limited data. We show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data.
  arXiv  Detail & Related papers  (2021-04-07T17:59:06Z)
• Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly [114.81028176850404]
  Training generative adversarial networks (GANs) with limited data generally results in deteriorated performance and collapsed models. We decompose the data-hungry GAN training into two sequential sub-problems. Such a coordinated framework enables us to focus on lower-complexity and more data-efficient sub-problems.
  arXiv  Detail & Related papers  (2021-02-28T05:20:29Z)
• A New Perspective on Stabilizing GANs training: Direct Adversarial Training [10.66166999381244]
  Training instability is still one of the open problems for all GAN-based algorithms. It is found that sometimes the images produced by the generator act like adversarial examples of the discriminator during the training process. We propose the Direct Adversarial Training method to stabilize the training process of GANs.
  arXiv  Detail & Related papers  (2020-08-19T02:36:53Z)
• Differentiable Augmentation for Data-Efficient GAN Training [48.920992130257595]
  We propose DiffAugment, a simple method that improves the data efficiency of GANs by imposing various types of differentiable augmentations on both real and fake samples. Our method can generate high-fidelity images using only 100 images without pre-training, while being on par with existing transfer learning algorithms.
  arXiv  Detail & Related papers  (2020-06-18T17:59:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.