PacGAN: The power of two samples in generative adversarial networks

Lin, Zinan; Khetan, Ashish; Fanti, Giulia; Oh, Sewoong

doi:10.48550/arxiv.1712.04086

Cited by 42 publications

(43 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It proposes dynamics-based approaches for avoiding mode collapse showing local convergence to Nash-equilibrum. Recently, PacGAN [8] is introduced that simply extends discriminator input for packed with multiple samples showing state-of-the-art mode detection performance.…”

Section: Related Workmentioning

confidence: 99%

“…We employ three metrics for quantitative evaluation: number of modes found, high quality sample ratio (HQS) [13], and additional distribution distance measurement Jensen-Shannon divergence (JSD). Number of Gaussian modes (8,25,25, and 27, respectively) found with generated samples and high quality sample ratio (HQS) are counted 20 times and mean and std. are calculated.…”

Section: Mixture Of Gaussiansmentioning

confidence: 99%

“…Proposed method shows outstanding convergence in both measurements. Recently, a new approach called PacGAN is proposed [8] that modifies the discriminator to make decisions based on multiple samples from the same class. This simple idea is tested on exist-ing GANs showing outstanding performance in addressing mode collapse problem.…”

Section: Mixture Of Gaussiansmentioning

confidence: 99%

See 2 more Smart Citations

Mode Penalty Generative Adversarial Network with adapted Auto-encoder

Lee,

Lee

2020

Preprint

View full text Add to dashboard Cite

Generative Adversarial Networks (GAN) are trained to generate sample images of interest distribution. To this end, generator network of GAN learns implicit distribution of real data set from the classification with candidate generated samples. Recently, various GANs have suggested novel ideas for stable optimizing of its networks. However, in real implementation, sometimes they still represent a only narrow part of true distribution or fail to converge. We assume this ill posed problem comes from poor gradient from objective function of discriminator, which easily trap the generator in a bad situation. To address this problem, we propose a mode-penalty GAN combined with pre-trained autoencoder for explicit representation of generated and real data samples in the encoded space. In this space, we make a generator manifold to follow a real manifold by finding entire modes of target distribution. In addition, penalty for uncovered modes of target distribution is given to the generator which encourages it to find overall target distribution. We demonstrate that applying the proposed method to GANs helps generator's optimization becoming more stable and having faster convergence through experimental evaluations. Recently, generative networks have been widely

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Mixture Of Gaussiansmentioning

confidence: 99%

See 1 more Smart Citation

Mode Penalty Generative Adversarial Network with adapted Auto-encoder

Lee,

Lee

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…There exists a rich set of works improving classic generative models for alleviating missing modes, especially in the framework of GANs, by altering objective functions [13,14,15,10,16,17], changing training methods [18,19], modifying neural network architectures [2,20,21,22,23], or regularizing latent space distributions [4,24]. The general philosophy behind these improvements is to reduce the statistical distance between the generated distribution and target distribution by making the models easier to train.…”

Section: Related Workmentioning

confidence: 99%

Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach

Zhong,

Mo,

Xiao

et al. 2019

Preprint

View full text Add to dashboard Cite

Many generative models have to combat missing modes. The conventional wisdom to this end is by reducing through training a statistical distance (such as f -divergence) between the generated distribution and provided data distribution. But this is more of a heuristic than a guarantee. The statistical distance measures a global, but not local, similarity between two distributions. Even if it is small, it does not imply a plausible mode coverage. Rethinking this problem from a game-theoretic perspective, we show that a complete mode coverage is firmly attainable. If a generative model can approximate a data distribution moderately well under a global statistical distance measure, then we will be able to find a mixture of generators that collectively covers every data point and thus every mode, with a lower-bounded generation probability. Constructing the generator mixture has a connection to the multiplicative weights update rule, upon which we propose our algorithm. We prove that our algorithm guarantees complete mode coverage. And our experiments on real and synthetic datasets confirm better mode coverage over recent approaches, ones that also use generator mixtures but rely on global statistical distances.

show abstract

“…In Figure 5 in Appendix J, we show example images from the three generators for the different flipping probabilities. We believe that the gain in using the proposed robust GANs will be larger, when we train to higher accuracy with larger networks and extensive hyper parameter tuning, with latest innovations in GAN architectures, for example [54,28,17,19,41].…”

Section: Cifar-10mentioning

confidence: 99%

Robustness of Conditional GANs to Noisy Labels

Thekumparampil,

Khetan,

Lin

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on whether the noise model is known or not. When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN). The main idea is to corrupt the label of the generated sample before feeding to the adversarial discriminator, forcing the generator to produce samples with clean labels. This approach of passing through a matching noisy channel is justified by corresponding multiplicative approximation bounds between the loss of the RCGAN and the distance between the clean real distribution and the generator distribution. This shows that the proposed approach is robust, when used with a carefully chosen discriminator architecture, known as projection discriminator. When the distribution of the noise is not known, we provide an extension of our architecture, which we call RCGAN-U, that learns the noise model simultaneously while training the generator. We show experimentally on MNIST and CIFAR-10 datasets that both the approaches consistently improve upon baseline approaches, and RCGAN-U closely matches the performance of RCGAN.

show abstract

PacGAN: The power of two samples in generative adversarial networks

Cited by 42 publications

References 0 publications

Mode Penalty Generative Adversarial Network with adapted Auto-encoder

Mode Penalty Generative Adversarial Network with adapted Auto-encoder

Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach

Robustness of Conditional GANs to Noisy Labels

Contact Info

Product

Resources

About