Abstract
Given recent advances in deep learning, semi-supervised techniques have seen a rise in interest. Generative adversarial networks (GANs) represent one recent approach to semi-supervised learning (SSL). This paper presents a survey method using GANs for SSL. Previous work in applying GANs to SSL are classified into pseudo-labeling/classification, encoder-based, TripleGAN-based, two GAN, manifold regularization, and stacked discriminator approaches. A quantitative and qualitative analysis of the various approaches is presented. The R3-CGAN architecture is identified as the GAN architecture with state-of-the-art results. Given the recent success of non-GAN-based approaches for SSL, future research opportunities involving the adaptation of elements of SSL into GAN-based implementations are also identified.
Highlights
With recent advances in deep learning and its applications, research opportunities in the area have expanded and diversified in different directions
Generative adversarial networks (GANs) were effective at taking a latent and generating authors were effective at taking a latent spacespace and generating data, data, was thereno was no technique for GANs to project the data the latent space
An interesting technique was proposed by SVMGAN [44], that tried to solve the issue of GAN-based supervised learning (SSL) models being sensitive to local perturbations by introducing a was used as part of the attention-based GAN architecture, while manifold regularization based on [42] was added as an additional regularization term to the loss function to make full use of unlabeled samples using a Monte Carlo approximation
Summary
With recent advances in deep learning and its applications, research opportunities in the area have expanded and diversified in different directions. Semi-supervised learning relies on the assumption that the data distribution over the input space embeds significant information about the distribution of the labels in the output space [1]. Points can be on connected byofshort that dothe notdecision pass through low-density [4] The basis this curves assumption, boundary should regions not cross. Thesecond secondassumption, assumption,called calledthe thelow-density low-densityassumption, assumption,states statesthat thatthe thedecision decision boundaryininaaclassifier classifier should pass inin thethe input space [1].[1]. This assumption area in the input space where the probability of a data point existing is low
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have