Semi-supervised Learning With Bidirectional Gans

Abstract

In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner. The presented method utilizes triplet loss function as an additional component of the objective function used to train discriminative data representation in the latent space of the BiGAN model. This representation can be further used as a seed for generating artificial images, but also as a good feature embedding for classification and image retrieval tasks. We evaluate the quality of the proposed method in the two mentioned challenging tasks using two benchmark datasets: CIFAR10 and SVHN.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyzamorski2018semi

Related papers

• Training Triplet Networks With GAN (2017)0.00
• Bingan: Learning Compact Binary Descriptors With A Regularized GAN (2018)0.00
• SCH-GAN: Semi-supervised Cross-modal Hashing By Generative Adversarial Network (2018)15.03
• Binary Generative Adversarial Networks For Image Retrieval (2017)18.34
• Deep Semantic Hashing With Generative Adversarial Networks (2018)13.50
• Inverting The Generator Of A Generative Adversarial Network (2016)17.61
• Generative Adversarial Nets For Information Retrieval: Fundamentals And Advances (2018)0.00
• Text-to-image Generation Via Implicit Visual Guidance And Hypernetwork (2022)0.00