Arşiv ve Dokümantasyon Merkezi
Dijital Arşivi

Training bidirectional generative adverarial networks with hints

Basit öğe kaydını göster

dc.contributor Graduate Program in Computer Engineering.
dc.contributor.advisor Alpaydın, Ethem.
dc.contributor.author Mutlu, Uras.
dc.date.accessioned 2023-03-16T10:03:48Z
dc.date.available 2023-03-16T10:03:48Z
dc.date.issued 2019.
dc.identifier.other CMPE 2019 M87
dc.identifier.uri http://digitalarchive.boun.edu.tr/handle/123456789/12374
dc.description.abstract The generative adversarial network (GAN) is a deep learning architecture that learns a generative model by training a later discriminator to best differentiate “fake” examples generated by the generator from the “true” examples sampled from the train ing set. The generator of GAN takes a low-dimensional latent space vector as input and learns to generate the corresponding input example. The aim of the generator is to gen erate examples that can not be separated from the true examples by the discriminator. The aim of the discriminator is to maximize the separability of the generated exam ples from the true examples. A recent extension is the bidirectional GAN (BiGAN) where an encoder is also trained in the inverse direction to generate the latent space vector for a given training example. Recently, Wasserstein GAN has been proposed for GAN and our first contribution is to adapt Wasserstein loss to BiGANs. The added encoder of the BiGAN also allows us to define auxiliary reconstruction losses as hints to learn a better generator, and this is our second contribution. Through experiments on five image data sets, namely, MNIST, UT-Zap50K, GTSRB, Cifar10, and CelebA, we show that Wasserstein BiGANs, augmented with hints, learn better generators in terms of image generation quality and diversity, as measured visually by analyzing the generated samples, and numerically by the 1-nearest-neighbor test.
dc.format.extent 30 cm.
dc.publisher Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018.
dc.subject.lcsh Natural language processing (Computer science)
dc.title Training bidirectional generative adverarial networks with hints
dc.format.pages xv, 62 leaves ;


Bu öğenin dosyaları

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster

Dijital Arşivde Ara


Göz at

Hesabım