Text

Triple Generative Adversarial Networks

We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN). The generator and the classifier characterize the conditional distributions between images and labels to perform conditional generation and classification, respectively. The discriminator solely focuses on identifying fake image-label pairs. Theoretically, the three-player formulation guarantees consistency. Namely, under a nonparametric assumption, the unique equilibrium of the game is that the distributions characterized by the generator and the classifier converge to the data distribution. As a byproduct of the three-player formulation, Triple-GAN is flexible to incorporate different semi-supervised classifiers and GAN architectures. We evaluate Triple-GAN in two challenging settings, namely, semi-supervised learning and the extremely low data regime. In both settings, Triple-GAN can achieve excellent classification results and generate meaningful samples in a specific class simultaneously. In particular, using a commonly adopted 13-layer CNN classifier, Triple-GAN outperforms extensive semi-supervised learning methods substantially on several benchmarks no matter data augmentation is applied or not.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.12 Part 2 December 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 9629-9640

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

SEMI SUPERVISED LEARNING
GENERATIVE ADVERSARIAL NETWORK
DEEP GENERATIVE MODEL
EXTREMELY LOW DATA REGIME
CONDITIONAL IMAGE GENERATION

Info Detail Spesifik

10.1109/TPAMI.2021.3127558

Pernyataan Tanggungjawab

Chongxuan Li, Kun Xu, Jun Zhu, Jiashuo Liu, Bo Zhang

Versi lain/terkait

Lampiran Berkas

Komentar