Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference

By Abhishek Kumar, Prasanna Sattigeri, Tom Fletcher. 2017

161 citations recorded by the source corpus.

Subfields: Generative Models, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

In Representation & Self-Supervised Learning

Citations in the corpus

Learning deep representations by mutual information estimation and maximization (2018, background): “al., 2016). In generative adversarial networks (GANs, Goodfellow et al., 2014), the representation of the discriminator has been shown to be suitable for some downstream tasks (Salimans et al., 2016; Kumar et al., 2017). While little explanation is provided on why GANs should learn good representati”
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation (2020, background): “Thus, learning from less expensive data [Kumar et al. , 2017; Sakai et al. , 2017] has been extensively studied in machine learning ﬁeld, including label-noise learning [Han et al. , 2018b; Han et al. , 2018a], complementary-label learning [Ishida et al. , 2019; Yu et al. , 2018; Ishida et al. ,…”
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey (2022, background): “When re-formulated as a semi-supervised representation learner, GANs can leverage the benefits of both unsupervised generative modeling and supervised discriminative learning [66], [67], [68], [69], [113], [114], [115], [116], [117], [118].”
Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation (2020, methodology): “SSL approaches such as self-training [2, 37, 49], co-training [5, 70] and GAN based methods [11,32] have been widely applied to UDA [9,14,24,55,61,72,73], and vice versa.”
A Survey on Deep Semi-Supervised Learning (2021, background): “CatGAN [32] 1:39ð 0:28Þ 19:58ð 0:58Þ ImprovedGAN [33] 0:93ð 0:07Þ 18:44ð 4:8Þ 8:11ð 1:3Þ 21:83ð 2:01Þ 18:63ð 2:32Þ GoodBadGAN [34] 0:80ð 0:1Þ 4:25ð 0:03Þ 14:41ð 0:30Þ Localized GAN [35] 5:48ð 0:29Þ 4:73ð 0:16Þ 17:44ð 0:25Þ 14:23ð 0:27Þ CT-GAN [36] 0:89ð 0:13Þ 9:98ð 0:21Þ ALI [37] 7:42ð 0:65Þ 19:98ð ”
An Incremental Self-Labeling Strategy for Semi-Supervised Deep Learning Based on Generative Adversarial Networks (2020, methodology): “For the task of semi-supervised learning with GANs, most of the existing works use a GAN-based model by modifying the regular GAN’s discriminator D(·) to determine k outputs corresponding to k classes[4] and, in most cases, a (k + 1)th virtual output corresponding to fake samples from the generator ”
Semi-supervised Learning on Graphs with Generative Adversarial Nets (2018, methodology): “resent a novel method GraphSGAN for semi-supervised learning on graphs with GANs. GraphSGAN maps graph topologies intofeaturespaceandjointlytrainsgeneratornetworkandclassifier network. Previous works [8, 18] tried to explain semi-supervised GANs’ working principles, but only found that generating mo”
Semi-Supervised Semantic Segmentation With Cross-Consistency Training (2020, background): “Some newly introduced techniques are based on generative modeling [28, 49].”
An Overview of Deep Semi-Supervised Learning (2020, background): “[88] proposed Augmented-BiGAN, an improved version of BiGAN for SSL.”