paper-with-me

Papers

Self-Supervised GANs via Auxiliary Rotation Loss

2018-11-27 · CVPR 2019 6 · Ting Chen, Xiaohua Zhai, Marvin Ritter, Mario Lucic, Neil Houlsby

Conditional GANs are at the forefront of natural image synthesis. The main drawback of such models is the necessity for labeled data. In this work we exploit two popular unsupervised learning techniques, adversarial training and self-supervision, and take a step towards bridging the gap between conditional and unconditional GANs. In particular, we allow the networks to collaborate on the task of representation learning, while being adversarial with respect to the classic GAN game. The role of self-supervision is to encourage the discriminator to learn meaningful feature representations which are not forgotten during training. We test empirically both the quality of the learned image representations, and the quality of the synthesized images. Under the same conditions, the self-supervised GAN attains a similar performance to state-of-the-art conditional counterparts. Finally, we show that this approach to fully unsupervised learning can be scaled to attain an FID of 23.4 on unconditional ImageNet generation.

📄 PDF Abstract BibTeX arXiv:1811.11212

Code (4)

google/compare_gan 공식 구현 tf
sanidhyamangal/SSLGAN pytorch
vandit15/Self-Supervised-Gans-Pytorch pytorch
zhangqianhui/Self-Supervised-GANs tf

Tasks

Image GenerationRepresentation Learning

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks

2020-11-03 · Gulcin Baykal, Furkan Ozcelik, Gozde Unal

Generative Adversarial Networks (GANs) have become the most used networks towards solving the problem of image generation. Self-supervised GANs are later proposed to avoid the catastrophic forgetting of the discriminator…

Image Generation

MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network

2020-06-11 · Jiaze Sun, Binod Bhattarai, Tae-Kyun Kim

We present a novel self-supervised learning approach for conditional generative adversarial networks (GANs) under a semi-supervised setting. Unlike prior self-supervised approaches which often involve geometric augmentat…

AttributeGenerative Adversarial NetworkSelf-Supervised Learning

FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss

2022-01-29 · Jinbao Wang, Guoyang Xie, Yawen Huang, Yefeng Zheng 외

The existence of completely aligned and paired multi-modal neuroimaging data has proved its effectiveness in the diagnosis of brain diseases. However, collecting the full set of well-aligned and paired data is impractica…

Data AugmentationImage GenerationSelf-Supervised Learning

Unsupervised Deep Metric Learning via Auxiliary Rotation Loss

2019-11-16 · Xuefei Cao, Bor-Chun Chen, Ser-Nam Lim

Deep metric learning is an important area due to its applicability to many domains such as image retrieval and person re-identification. The main drawback of such models is the necessity for labeled data. In this work, w…

ClusteringImage RetrievalMetric LearningPerson Re-Identification+1

Tailoring Self-Supervision for Supervised Learning

2022-07-20 · WonJun Moon, Ji-Hwan Kim, Jae-Pil Heo

Recently, it is shown that deploying a proper self-supervision is a prospective way to enhance the performance of supervised learning. Yet, the benefits of self-supervision are not fully exploited as previous pretext tas…

Adversarial RobustnessData AugmentationImage Classificationimbalanced classification+2