Conditional generative adversarial nets for convolutional face generation

By Jon Gauthier. 2015

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

Citations in the corpus

Generative Adversarial Networks (2021, neutral): “Several types of GAN architectures have been proposed, including deep convolutional GANs, Wasserstein GANs [7], and conditional GANs [8].”
Image-to-Image Translation with Conditional Adversarial Networks (2016, background): “Prior and concurrent works have conditioned GANs on discrete labels [38, 21, 12], text [43], and, indeed, images.”
Generative Adversarial Text to Image Synthesis (2016, methodology): “In the generator G , ﬁrst we sample from the noise prior z ∈ R Z ∼ N (0 , 1) and we encode the text query t us-ing text encoder ϕ .”
Cross-Modal Contrastive Learning for Text-to-Image Generation (2021, background): “Generative Adversarial Networks (GANs) [12] have shown promising results on text-to-image generation [44, 61, 62], using a conditional GAN formulation [11].”
Coupled Generative Adversarial Networks (2016, methodology): “Following [5], several works improved the image generation quality of GAN, including a Laplacian pyramid implementation[29], a deeper architecture[12], and conditional models[13, 14].”
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization (2016, methodology): “We believe that in the future the true benefits of neural samplers for representing uncertainty will be found in discriminative models and our presented methods extend readily to this case by providing additional inputs to both the generator and variational function as in the conditional GAN model [”
Generating images with recurrent adversarial networks (2016, methodology): “As shown by [2], ignoring the style-cost in this approach and only matching image features, it is possible to render images which are similar to the 1 ar X iv :1 60 2.”
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks (2016, background): “Conditional GAN [7, 19] is an extension of GAN where both the generator and discriminator receive additional conditioning variables c, yielding G(z, c) and D(x, c).”
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks (2017, background): “[48] factorized image generation into foreground and background generation with layered recursive GANs.”
Stacked Generative Adversarial Networks (2016, background): “Some previous works [40, 15, 5] tackle this problem by feeding the conditional information to both the generator and discriminator.”
Attribute2Image: Conditional Image Generation from Visual Attributes (2015, background): “Recently, the generative adversarial networks (GANs) [12, 10, 6] have been developed for image generation.”
DISCO Nets : DISsimilarity COefficients Networks (2016, neutral): “Gauthier [4] applies cGAN to face generation.”
Censoring Representations with an Adversary (2015, methodology): “Goodfellow et al. (2014) the idea of using an adversary to learn a generative model of data was introduced and followed-up by work such as Gauthier (2015), Rudy & Taylor (2014) and Denton et al. (2015).”
Generative Multi-Adversarial Networks (2016, background): “Work extending GANs to semi-supervised learning (Chen et al. (2016); Mirza & Osindero (2014); Gauthier (2014); Springenberg (2015)), inference (Makhzani et al. (2015); Dumoulin et al. (2016)), feature learning (Donahue et al. (2016)), and improved image generation (Im et al. (2016); Denton et al.…”
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis (2016, methodology): “[9] extend this model by a Laplacian pyramid.”
Image Generation from Scene Graphs (2018, background): “GANs can be conditioned on category labels by providing labels as an additional input to both generator and discriminator [10, 35] or by forcing the discriminator to predict the label [37]; we take the latter approach.”
Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs (2017, background): “The success of GANs in generating realistic-looking images [21, 15, 8, 22] suggests their applicability for this task, however limited work has exploited them for generating time-series data.”