CoChat
Cited by 248

The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.

MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks

Open access
Karnewar, Animesh, Wang, Oliver · 2020 · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

While Generative Adversarial Networks (GANs) have seen huge successes in image synthesis tasks, they are notoriously difficult to adapt to different datasets, in part due to instability during training and sensitivity to hyperparameters. One commonly accepted reason for this instability is that gradients passing from the discriminator to the generator become uninformative when there isn't enough overlap in the supports of the real and fake distributions. In this work, we propose the Multi-Scale Gradient Generative Adversarial Network (MSG-GAN), a simple but effective technique for addressing this by allowing the flow of gradients from the discriminator to the generator at multiple scales. This technique provides a stable approach for high resolution image synthesis, and serves as an alternative to the commonly used progressive growing technique. We show that MSG-GAN converges stably on a variety of image datasets of different sizes, resolutions and domains, as well as different types of loss functions and architectures, all with the same set of fixed hyperparameters. When compared to state-of-the-art GANs, our approach matches or exceeds the performance in most of the cases we tried.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr42600.2020.00782

Cites

11 of 11 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 31

  1. zhang, 2017, Stack-gan++ Realistic image synthesis with stacked generative adversarial networks
  2. wang, 2017, Magan: Margin adaptation for generative adversarial networks, ArXiv abs/1704 03817
  3. van den oord, 2016, Pixel recurrent neural networks, CoRR abs/1601 06759
  4. van den oord, 2016, Conditional image generation with pixelcnn decoders, Advances in neural information processing systems
  5. sønderby, 2016, Amortised MAP inference for image super-resolution, ArXiv abs/1610 04490
  6. yazici, 0, The unusual effectiveness of averaging in GAN training, International Conference on Learning Representations
  7. yang, 2017, Lr-gan: Layered recursive generative adversarial networks for image generation, ICLRE
  8. 10.1109/TPAMI.2007.60 · DOI · Paper page
  9. 10.1109/CVPR.2018.00917 · DOI · Paper page
  10. goodfellow, 2014, Generative adversarial nets, Advances in neural information processing systems
  11. 10.1109/CVPR.2018.00649 · DOI · Paper page
  12. jolicoeur-martineau, 0, The relativistic discriminator: a key element missing from standard GAN, International Conference on Learning Representations
  13. karras, 2018, Progressive growing of GANs for improved quality, stability, and variation, ICLRE
  14. kingma, 2018, Glow: Generative flow with invertible 1x1 convolutions, Advances in neural information processing systems
  15. kodali, 2017, On convergence and stability of GANs, ArXiv Preprint
  16. rezende, 2015, Variational inference with normalizing flows, ICML
  17. brock, 0, Large scale GAN training for high fidelity natural image synthesis, International Conference on Learning Representations
  18. salimans, 2017, PixelCNN++: A PixelCNN implementation with discretized logistic mixture likelihood and other modifications, ICLRE
  19. denton, 2015, Deep generative image models using a laplacian pyramid of adversarial networks, NIPS
  20. durugkar, 2016, Generative multi-adversarial networks, ArXiv Preprint
  21. dinh, 2016, Density estimation using real NVP, CoRR
  22. arjovsky, 2017, Wasserstein generative adversarial networks, ICML
  23. arnab, 2018, Multi-agent diverse generative adversarial networks, CVPR
  24. arjovsky, 2017, Towards principled methods for training generative adversarial networks, CoRR
  25. 10.1145/1186822.1073261 · doi:10.1145/1186822.1073261
  26. xudong, 2016, and Zhen Wang. Multi-class generative adversarial networks with the 12 loss function, ArXiv abs/1611 04076
  27. lin, 2018, PacGAN: The power of two samples in generative adversarial networks, Advances in neural information processing systems
  28. metz, 2016, Unrolled generative adversarial networks
  29. zhu, 2017, Toward multimodal image-to-image translation, Advances in neural information processing systems
  30. mescheder, 2018, Which training methods for GANs do actually converge?, ICML
  31. peng, 2019, Variational discriminator bottleneck: Improving imitation learning, inverse RL, and GANs by constraining information flow, ICLRE

Cited by

See all 248

Metadata

Authors
Karnewar, A., & Wang, O.
Venue
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2020-06
Pages
7796-7805
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3035231706
Cited by
248
References
11
FWCI
14.27
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.