Omni-GAN: On the Secrets of cGANs and Beyond

@article{Zhou2021OmniGANOT,
  title={Omni-GAN: On the Secrets of cGANs and Beyond},
  author={Peng Zhou and Lingxi Xie and Bingbing Ni and Qi Tian},
  journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2021},
  pages={14041-14051}
}
  • P. Zhou, Lingxi Xie, Qi Tian
  • Published 26 November 2020
  • Computer Science
  • 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
The conditional generative adversarial network (cGAN) is a powerful tool of generating high-quality images, but existing approaches mostly suffer unsatisfying performance or the risk of mode collapse. This paper presents Omni-GAN, a variant of cGAN that reveals the devil in designing a proper discriminator for training the model. The key is to ensure that the discriminator receives strong supervision to perceive the concepts and moderate regularization to avoid collapse. Omni-GAN is easily… 
Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training
TLDR
This paper identifies that gradient exploding in the classifier can cause an undesirable collapse in early training, and projects input vectors onto a unit hypersphere can resolve the problem, and proposes the Data-to-Data Cross-Entropy loss (D2D-CE) to exploit relational information in theclass-labeled dataset.
StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis
TLDR
The taxonomy of GAN approaches is studied and a new open-source library named StudioGAN is presented, which provides GAN implementations, training, and evaluation scripts with the pre-trained weights.
Tail-GAN: Nonparametric Scenario Generation for Tail Risk Estimation
TLDR
This work designs a Generative Adversarial Network architecture capable of learning to simulate price scenarios that preserve tail risk features for these benchmark trading strategies, leading to consistent estimators for their Value-at-Risk and Expected Shortfall.
Manifold Learning Benefits GANs
TLDR
This paper improves Generative Adversarial Networks by incorporating a manifold learning step into the discriminator, and finds that localityconstrained non-linear manifolds outperform linear manifolds due to their non-uniform density and smoothness.
DGL-GAN: Discriminator Guided Learning for GAN Compression
TLDR
A novel yet simple Discriminator Guided Learning approach for compressing vanilla GAN, dubbed DGL-GAN, which is valid since empirically, learning from the teacher discriminator could facilitate the performance of student GANs and achieves state-of-the-art results.
Multiclass Image Classification Using GANs and CNN Based on Holes Drilled in Laminated Chipboard
TLDR
The aim of the research was to create a model capable of identifying different levels of quality of the holes, where the reduced quality would serve as a warning that the drill is about to wear down, which could reduce the damage caused by a blunt tool.
cGANs with Auxiliary Discriminative Classifier
TLDR
It is pointed out that the fundamental reason is that the classifier of AC-GAN is generator-agnostic, and thus cannot provide informative guidance to the generator to approximate the target joint distribution, leading to a minimization of conditional entropy that decreases the intra-class diversity.
Conditional GANs with Auxiliary Discriminative Classifier
TLDR
The theoretical analysis reveals that the generator can faithfully learn the joint distribution even without the original discriminator, making the proposed ADC-GAN robust to the value of the coefficient hyperparameter and the selection of the GAN loss, and stable during training.

References

SHOWING 1-10 OF 90 REFERENCES
Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks
TLDR
A novel idea that adopts NAS to find a distinct architecture for each class, and delivers several insights that are helpful in designing efficient GAN models.
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.
Training Generative Adversarial Networks with Limited Data
TLDR
It is demonstrated, 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, and is expected to open up new application domains for GANs.
cGANs with Projection Discriminator
TLDR
With this modification, the quality of the class conditional image generation on ILSVRC2012 (ImageNet) 1000-class image dataset is significantly improved and the application to super-resolution was extended and succeeded in producing highly discriminative super- resolution images.
Progressive Growing of GANs for Improved Quality, Stability, and Variation
TLDR
A new training methodology for generative adversarial networks is described, starting from a low resolution, and adding new layers that model increasingly fine details as training progresses, allowing for images of unprecedented quality.
A Style-Based Generator Architecture for Generative Adversarial Networks
TLDR
An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation.
cGANs with Multi-Hinge Loss
TLDR
The proposed new algorithm to incorporate class conditional information into the discriminator of GANs via a multi-class generalization of the commonly used Hinge loss shows that learning a single good classifier and a single state of the art generator simultaneously is possible in supervised and semi-supervised settings.
Adversarial Discriminative Domain Adaptation
TLDR
It is shown that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and the promise of the approach is demonstrated by exceeding state-of-the-art unsupervised adaptation results on standard domain adaptation tasks as well as a difficult cross-modality object classification task.
Large Scale GAN Training for High Fidelity Natural Image Synthesis
TLDR
It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input.
Spectral Normalization for Generative Adversarial Networks
TLDR
This paper proposes a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator and confirms that spectrally normalized GANs (SN-GANs) is capable of generating images of better or equal quality relative to the previous training stabilization techniques.
...
...