.png){kind=icon}
返回
Self-Supervised Adversarial Variational Learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.110156.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A natural approach for representation learning is to combine the inference mechanisms of VAEs and the generative abilities of GANs, within a new model, namely VAEGAN. Most existing VAEGAN models would jointly train the generator and inference modules, which has limitations when learning representations generated by a pre-trained GAN model without data. In this paper, we develop a novel hybrid model, called the Self-Supervised Adversarial Variational Learning (SS-AVL) which introduces a two-step optimization procedure training separately the generator and the inference model. The primary advantage of SS-AVL over existing VAEGAN models is that SS-AVL optimizes the inference models in a self-supervised learning manner where the samples used for training the inference models are drawn from the generator distribution instead of using real samples. This can allow SS-AVL to learn representations from arbitrary GAN models without using real data. Additionally, we employ information maximization into the context of increasing the maximum likelihood, which encourages SS-AVL to learn meaningful latent representations. We perform extensive experiments to demonstrate the effectiveness of the proposed SS-AVL model.
Keyword:
Self-supervised learning
Variational Autoencoders (VAE)
Generative Adversarial Nets (GAN)
Representation learning
Mutual information
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Learning image compressed sensing with sub-pixel convolutional generative adversarial network.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Two‐Stage Robust Optimization Model for Fresh Cold Chain considering Carbon Emissions and UncertaintyComplexity
OAAI
ComplexityIF0
OAAI分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容