Projected GANs Converge Faster

• URL: http://arxiv.org/abs/2111.01007v1
• Date: Mon, 1 Nov 2021 15:11:01 GMT
• Title: Projected GANs Converge Faster
• Authors: Axel Sauer, Kashyap Chitta, Jens M\"uller, Andreas Geiger
• Abstract summary: Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. We make significant headway on these issues by projecting generated and real samples into a fixed, pretrained feature space. Our Projected GAN improves image quality, sample efficiency, and convergence speed.
• Score: 50.23237734403834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-parameter sweeps. We make significant headway on these issues by projecting generated and real samples into a fixed, pretrained feature space. Motivated by the finding that the discriminator cannot fully exploit features from deeper layers of the pretrained model, we propose a more effective strategy that mixes features across channels and resolutions. Our Projected GAN improves image quality, sample efficiency, and convergence speed. It is further compatible with resolutions of up to one Megapixel and advances the state-of-the-art Fr\'echet Inception Distance (FID) on twenty-two benchmark datasets. Importantly, Projected GANs match the previously lowest FIDs up to 40 times faster, cutting the wall-clock time from 5 days to less than 3 hours given the same computational resources.

Related papers

• High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity [69.32473738284374]
  We propose DiffDIS, a diffusion-driven segmentation model that taps into the potential of the pre-trained U-Net within diffusion models. By leveraging the robust generalization capabilities and rich, versatile image representation prior to the SD models, we significantly reduce the inference time while preserving high-fidelity, detailed generation. Experiments on the DIS5K dataset demonstrate the superiority of DiffDIS, achieving state-of-the-art results through a streamlined inference process.
  arXiv  Detail & Related papers  (2024-10-14T02:49:23Z)
• Faster Projected GAN: Towards Faster Few-Shot Image Generation [10.068622488926172]
  This paper proposes an improved GAN network model, which is named Faster Projected GAN, based on Projected GAN. By introducing depth separable convolution (DSC), the number of parameters of the Projected GAN is reduced, the training speed is accelerated, and memory is saved.
  arXiv  Detail & Related papers  (2024-01-23T07:55:27Z)
• Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation [1.3764085113103222]
  Single-Image Super-Resolution can support robotic tasks in environments where a reliable visual stream is required. We propose an efficient Generative Adversarial Network model for real-time Super-Resolution, called EdgeSRGAN.
  arXiv  Detail & Related papers  (2022-09-07T10:58:41Z)
• Time Efficient Training of Progressive Generative Adversarial Network using Depthwise Separable Convolution and Super Resolution Generative Adversarial Network [0.0]
  We propose a novel pipeline that combines Progressive GAN with slight modifications and Super Resolution GAN. Super Resolution GAN up samples low-resolution images to high-resolution images which can prove to be a useful resource to reduce the training time exponentially.
  arXiv  Detail & Related papers  (2022-02-24T19:53:37Z)
• FMD-cGAN: Fast Motion Deblurring using Conditional Generative Adversarial Networks [26.878173373199786]
  We present a Fast Motion Deblurring-Conditional Generative Adversarial Network (FMD-cGAN) that helps in blind motion deblurring of a single image. FMD-cGAN delivers impressive structural similarity and visual appearance after deblurring an image.
  arXiv  Detail & Related papers  (2021-11-30T14:30:44Z)
• Improved Transformer for High-Resolution GANs [69.42469272015481]
  We introduce two key ingredients to Transformer to address this challenge. We show in the experiments that the proposed HiT achieves state-of-the-art FID scores of 31.87 and 2.95 on unconditional ImageNet $128 times 128$ and FFHQ $256 times 256$, respectively.
  arXiv  Detail & Related papers  (2021-06-14T17:39:49Z)
• Fourier Space Losses for Efficient Perceptual Image Super-Resolution [131.50099891772598]
  We show that it is possible to improve the performance of a recently introduced efficient generator architecture solely with the application of our proposed loss functions. We show that our losses' direct emphasis on the frequencies in Fourier-space significantly boosts the perceptual image quality. The trained generator achieves comparable results with and is 2.4x and 48x faster than state-of-the-art perceptual SR methods RankSRGAN and SRFlow respectively.
  arXiv  Detail & Related papers  (2021-06-01T20:34:52Z)
• TWIST-GAN: Towards Wavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution [4.622977798361014]
  Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from a remotely sensed image with low spatial resolution. Deep learning and generative adversarial networks (GANs) have made breakthroughs for the challenging task of single image super-resolution (SISR)
  arXiv  Detail & Related papers  (2021-04-20T22:12:38Z)
• Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers [115.90778814368703]
  Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval scales. An alternative approach of using vision-text transformers with cross-attention gives considerable improvements in accuracy over the joint embeddings.
  arXiv  Detail & Related papers  (2021-03-30T17:57:08Z)
• Improving the Speed and Quality of GAN by Adversarial Training [87.70013107142142]
  We develop FastGAN to improve the speed and quality of GAN training based on the adversarial training technique. Our training algorithm brings ImageNet training to the broader public by requiring 2-4 GPUs.
  arXiv  Detail & Related papers  (2020-08-07T20:21:31Z)

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.