Improved Consistency Regularization for GANs

• URL: http://arxiv.org/abs/2002.04724v2
• Date: Mon, 14 Dec 2020 21:33:59 GMT
• Title: Improved Consistency Regularization for GANs
• Authors: Zhengli Zhao, Sameer Singh, Honglak Lee, Zizhao Zhang, Augustus Odena, Han Zhang
• Abstract summary: We propose several modifications to the consistency regularization procedure designed to improve its performance. For unconditional image synthesis on CIFAR-10 and CelebA, our modifications yield the best known FID scores on various GAN architectures. On ImageNet-2012, we apply our technique to the original BigGAN model and improve the FID from 6.66 to 5.38, which is the best score at that model size.
• Score: 102.17007700413326
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work has increased the performance of Generative Adversarial Networks (GANs) by enforcing a consistency cost on the discriminator. We improve on this technique in several ways. We first show that consistency regularization can introduce artifacts into the GAN samples and explain how to fix this issue. We then propose several modifications to the consistency regularization procedure designed to improve its performance. We carry out extensive experiments quantifying the benefit of our improvements. For unconditional image synthesis on CIFAR-10 and CelebA, our modifications yield the best known FID scores on various GAN architectures. For conditional image synthesis on CIFAR-10, we improve the state-of-the-art FID score from 11.48 to 9.21. Finally, on ImageNet-2012, we apply our technique to the original BigGAN model and improve the FID from 6.66 to 5.38, which is the best score at that model size.

Related papers

• Improving Generative Adversarial Networks for Video Super-Resolution [0.0]
  This research explores different ways to improve generative adversarial networks for video super-resolution tasks. We evaluate our results using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) The integration of these methods results in an 11.97% improvement in PSNR and an 8% improvement in SSIM compared to the baseline video super-resolution generative adversarial network (GAN) model.
  arXiv  Detail & Related papers  (2024-06-24T06:57:51Z)
• IG-CFAT: An Improved GAN-Based Framework for Effectively Exploiting Transformers in Real-World Image Super-Resolution [2.009766774844269]
  This paper extends the CFAT model to an improved GAN-based model called IG-CFAT. IG-CFAT incorporates a semantic-aware discriminator to reconstruct fine details more accurately. Our methodology adds wavelet loss to conventional loss functions of GAN-based super-resolution models to recover high-frequency details more efficiently.
  arXiv  Detail & Related papers  (2024-06-19T20:21:26Z)
• Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models [102.72940700598055]
  In reasoning tasks, even a minor error can cascade into inaccurate results. We develop a method that avoids introducing external resources, relying instead on perturbations to the input. Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks.
  arXiv  Detail & Related papers  (2024-03-04T16:21:54Z)
• Revisiting Consistency Regularization for Semi-Supervised Learning [80.28461584135967]
  We propose an improved consistency regularization framework by a simple yet effective technique, FeatDistLoss. Experimental results show that our model defines a new state of the art for various datasets and settings.
  arXiv  Detail & Related papers  (2021-12-10T20:46:13Z)
• Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition [61.87842307164351]
  We first propose an Identity-Aware CycleGAN (IACycleGAN) model that applies a new perceptual loss to supervise the image generation network. It improves CycleGAN on photo-sketch synthesis by paying more attention to the synthesis of key facial regions, such as eyes and nose. We develop a mutual optimization procedure between the synthesis model and the recognition model, which iteratively synthesizes better images by IACycleGAN.
  arXiv  Detail & Related papers  (2021-03-30T01:30:08Z)
• InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning [39.316605441868944]
  Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications. We propose a principled framework to simultaneously mitigate two fundamental issues in GANs: catastrophic forgetting of the discriminator and mode collapse of the generator. Our approach significantly stabilizes GAN training and improves GAN performance for image synthesis across five datasets.
  arXiv  Detail & Related papers  (2020-07-09T06:56:11Z)
• Image Augmentations for GAN Training [57.65145659417266]
  We provide insights and guidelines on how to augment images for both vanilla GANs and GANs with regularizations. Surprisingly, we find that vanilla GANs attain generation quality on par with recent state-of-the-art results.
  arXiv  Detail & Related papers  (2020-06-04T00:16:02Z)
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples [67.11669996924671]
  We introduce a simple (one line of code) modification to the Generative Adversarial Network (GAN) training algorithm. When updating the generator parameters, we zero out the gradient contributions from the elements of the batch that the critic scores as least realistic' We show that this top-k update' procedure is a generally applicable improvement.
  arXiv  Detail & Related papers  (2020-02-14T19:27:50Z)

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.