中文
相关论文

相关论文: Adversarial Training of Variational Auto-encoders …

200 篇论文

We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep…

计算机视觉与模式识别 · 计算机科学 2019-06-06 Xianxu Hou , Ke Sun , Linlin Shen , Guoping Qiu

Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN). GANs can produce realistic images, but they suffer from mode collapse and do not provide…

计算机视觉与模式识别 · 计算机科学 2020-12-22 Antoine Plumerault , Hervé Le Borgne , Céline Hudelot

We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the…

机器学习 · 计算机科学 2016-02-12 Anders Boesen Lindbo Larsen , Søren Kaae Sønderby , Hugo Larochelle , Ole Winther

Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the…

机器学习 · 计算机科学 2018-06-12 Lars Mescheder , Sebastian Nowozin , Andreas Geiger

In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior…

机器学习 · 计算机科学 2016-05-26 Alireza Makhzani , Jonathon Shlens , Navdeep Jaitly , Ian Goodfellow , Brendan Frey

We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…

计算机视觉与模式识别 · 计算机科学 2018-02-06 Jianmin Bao , Dong Chen , Fang Wen , Houqiang Li , Gang Hua

Variational autoencoders (VAEs) have recently been shown to be vulnerable to adversarial attacks, wherein they are fooled into reconstructing a chosen target image. However, how to defend against such attacks remains an open problem. We…

机器学习 · 统计学 2021-02-01 Matthew Willetts , Alexander Camuto , Tom Rainforth , Stephen Roberts , Chris Holmes

Variational autoencoders (VAEs) are one of the powerful likelihood-based generative models with applications in many domains. However, they struggle to generate high-quality images, especially when samples are obtained from the prior…

机器学习 · 计算机科学 2021-11-05 Jyoti Aneja , Alexander Schwing , Jan Kautz , Arash Vahdat

Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations. However, conventional VAEs often generate relatively blurry images due to their assumption of an isotropic Gaussian latent…

计算机视觉与模式识别 · 计算机科学 2025-04-21 Andrew Kiruluta

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…

Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However,…

机器学习 · 计算机科学 2019-02-18 Wenju Xu , Shawn Keshmiri , Guanghui Wang

Recent advances in deep learning have shown their ability to learn strong feature representations for images. The task of image clustering naturally requires good feature representations to capture the distribution of the data and…

计算机视觉与模式识别 · 计算机科学 2020-05-12 Vignesh Prasad , Dipanjan Das , Brojeshwar Bhowmick

We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the…

计算机视觉与模式识别 · 计算机科学 2024-03-21 Xianxu Hou , Linlin Shen , Ke Sun , Guoping Qiu

Variational Autoencoder (VAE) and its variations are classic generative models by learning a low-dimensional latent representation to satisfy some prior distribution (e.g., Gaussian distribution). Their advantages over GAN are that they can…

计算机视觉与模式识别 · 计算机科学 2020-09-24 Cong Geng , Jia Wang , Li Chen , Zhiyong Gao

The variational autoencoder (VAE) framework remains a popular option for training unsupervised generative models, especially for discrete data where generative adversarial networks (GANs) require workaround to create gradient for the…

机器学习 · 计算机科学 2019-04-24 Jason Chou , Gautam Hathi

Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part…

机器学习 · 统计学 2017-11-08 Akash Srivastava , Lazar Valkov , Chris Russell , Michael U. Gutmann , Charles Sutton

Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit…

计算机视觉与模式识别 · 计算机科学 2019-11-15 Prashnna K Gyawali , Rudra Saha , Linwei Wang , VSR Veeravasarapu , Maneesh Singh

The surrogate loss of variational autoencoders (VAEs) poses various challenges to their training, inducing the imbalance between task fitting and representation inference. To avert this, the existing strategies for VAEs focus on adjusting…

神经与进化计算 · 计算机科学 2024-04-02 Zhangkai Wu , Longbing Cao , Lei Qi

Generative adversarial networks (GANs) are capable of producing high quality image samples. However, unlike variational autoencoders (VAEs), GANs lack encoders that provide the inverse mapping for the generators, i.e., encode images back to…

机器学习 · 统计学 2018-12-20 Paul K. Rubenstein , Yunpeng Li , Dominik Roblek

Sequential recommendation as an emerging topic has attracted increasing attention due to its important practical significance. Models based on deep learning and attention mechanism have achieved good performance in sequential…

信息检索 · 计算机科学 2021-03-22 Zhe Xie , Chengxuan Liu , Yichi Zhang , Hongtao Lu , Dong Wang , Yue Ding
‹ 上一页 1 2 3 10 下一页 ›