Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Radford, Alec; Metz, Luke; Chintala, Soumith

doi:10.48550/arxiv.1511.06434

Cited by 2,804 publications

(4,123 citation statements)

References 21 publications

Supporting

Mentioning

3,740

Contrasting

Unclassified

Order By: Relevance

“…One of the popular variants of GANs is deep convolutional GAN (DCGAN) [43]. The DCGAN adopted convolutional neural networks instead of fully connected networks as in vanilla GAN for the generator and the discriminator.…”

Section: ) Deep Convolutional Gan (Dcgan)mentioning

confidence: 99%

A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysis

Saad¹,

O’Reilly²,

Rehmani³

2022

Preprint

View full text Add to dashboard Cite

In biomedical image analysis, the applicability of deep learning methods is directly impacted by the quantity of image data available. This is due to deep learning models requiring large image datasets to provide high-level performance. Generative Adversarial Networks (GANs) have been widely utilized to address data limitations through the generation of synthetic biomedical images. GANs consist of two models. The generator, a model that learns how to produce synthetic images based on the feedback it receives. The discriminator, a model that classifies an image as synthetic or real and provides feedback to the generator. Throughout the training process, a GAN can experience several technical challenges that impede the generation of suitable synthetic imagery. First, the mode collapse problem whereby the generator either produces an identical image or produces a uniform image from distinct input features. Second, the non-convergence problem whereby the gradient descent optimizer fails to reach a Nash equilibrium. Thirdly, the vanishing gradient problem whereby unstable training behavior occurs due to the discriminator achieving optimal classification performance resulting in no meaningful feedback being provided to the generator. These problems result in the production of synthetic imagery that is blurry, unrealistic, and less diverse. To date, there has been no survey article outlining the impact of these technical challenges in the context of the biomedical imagery domain. This work presents a review and taxonomy based on solutions to the training problems of GANs in the biomedical imaging domain. This survey highlights important challenges and outlines future research directions about the training of GANs in the domain of biomedical imagery.

show abstract

Section: ) Deep Convolutional Gan (Dcgan)mentioning

confidence: 99%

A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysis

Saad¹,

O’Reilly²,

Rehmani³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The advent of GANs led to their application in various fields like image generation [11], super-resolution [12], image inpainting [13,14], etc.. They usually contain two networks: a generator that learns to generate images and a discriminator that distinguishes between the generated fake image and real image.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Image to Image Translation for Multiple Retinal Pathology Synthesis in Optical Coherence Tomography Scans

Hemanth¹,

Girish²

2021

Preprint

View full text Add to dashboard Cite

Image to Image Translation (I2I) is a challenging computer vision problem used in numerous domains for multiple tasks. Recently, ophthalmology became one of the major fields where the application of I2I is increasing rapidly. One such application is the generation of synthetic retinal optical coherence tomographic (OCT) scans. Existing I2I methods require training of multiple models to translate images from normal scans to a specific pathology: limiting the use of these models due to their complexity. To address this issue, we propose an unsupervised multi-domain I2I network with pre-trained style encoder that translates retinal OCT images in one domain to multiple domains. We assume that the image splits into domain-invariant content and domain-specific style codes, and pre-train these style codes. The performed experiments show that the proposed model outperforms state-of-the-art models like MUNIT and CycleGAN synthesizing diverse pathological scans.

show abstract

“…On the other hand, there are only a few attempts to investigate the normalization technique for the generator. Radford et al [33] proposed the GAN architecture called DCGAN and empirically proved that a batch normalization (BN) [13] is effective for the generator. For a conditional GAN (cGAN) that focuses on producing class-conditional images, Dumoulin et al [8] introduced a conditional batch normalization (cBN) which performs different affine transformations according to a given condition.…”

Section: Introductionmentioning

confidence: 99%

Image Generation with Self Pixel-wise Normalization

Yeo¹,

Sagong²,

Park³

et al. 2022

Preprint

View full text Add to dashboard Cite

Region-adaptive normalization (RAN) methods have been widely used in the generative adversarial network (GAN)-based image-to-image translation technique. However, since these approaches need a mask image to infer the pixel-wise affine transformation parameters, they cannot be applied to the general image generation models having no paired mask images. To resolve this problem, this paper presents a novel normalization method, called self pixel-wise normalization (SPN), which effectively boosts the generative performance by performing the pixel-adaptive affine transformation without the mask image. In our method, the transforming parameters are derived from a self-latent mask that divides the feature map into the foreground and background regions. The visualization of the selflatent masks shows that SPN effectively captures a sin-

show abstract

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Cited by 2,804 publications

References 21 publications

A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysis

A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysis

Unsupervised Image to Image Translation for Multiple Retinal Pathology Synthesis in Optical Coherence Tomography Scans

Image Generation with Self Pixel-wise Normalization

Contact Info

Product

Resources

About