AS-IntroVAE: Adversarial Similarity Distance Makes Robust IntroVAE

Chang-Tien Lu, Shen Zheng, Zirui Wang, O. Dib, Gaurav Gupta
{"title":"AS-IntroVAE: Adversarial Similarity Distance Makes Robust IntroVAE","authors":"Chang-Tien Lu, Shen Zheng, Zirui Wang, O. Dib, Gaurav Gupta","doi":"10.48550/arXiv.2206.13903","DOIUrl":null,"url":null,"abstract":"Recently, introspective models like IntroVAE and S-IntroVAE have excelled in image generation and reconstruction tasks. The principal characteristic of introspective models is the adversarial learning of VAE, where the encoder attempts to distinguish between the real and the fake (i.e., synthesized) images. However, due to the unavailability of an effective metric to evaluate the difference between the real and the fake images, the posterior collapse and the vanishing gradient problem still exist, reducing the fidelity of the synthesized images. In this paper, we propose a new variation of IntroVAE called Adversarial Similarity Distance Introspective Variational Autoencoder (AS-IntroVAE). We theoretically analyze the vanishing gradient problem and construct a new Adversarial Similarity Distance (AS-Distance) using the 2-Wasserstein distance and the kernel trick. With weight annealing on AS-Distance and KL-Divergence, the AS-IntroVAE are able to generate stable and high-quality images. The posterior collapse problem is addressed by making per-batch attempts to transform the image so that it better fits the prior distribution in the latent space. Compared with the per-image approach, this strategy fosters more diverse distributions in the latent space, allowing our model to produce images of great diversity. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of AS-IntroVAE on image generation and reconstruction tasks.","PeriodicalId":119756,"journal":{"name":"Asian Conference on Machine Learning","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Asian Conference on Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2206.13903","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Recently, introspective models like IntroVAE and S-IntroVAE have excelled in image generation and reconstruction tasks. The principal characteristic of introspective models is the adversarial learning of VAE, where the encoder attempts to distinguish between the real and the fake (i.e., synthesized) images. However, due to the unavailability of an effective metric to evaluate the difference between the real and the fake images, the posterior collapse and the vanishing gradient problem still exist, reducing the fidelity of the synthesized images. In this paper, we propose a new variation of IntroVAE called Adversarial Similarity Distance Introspective Variational Autoencoder (AS-IntroVAE). We theoretically analyze the vanishing gradient problem and construct a new Adversarial Similarity Distance (AS-Distance) using the 2-Wasserstein distance and the kernel trick. With weight annealing on AS-Distance and KL-Divergence, the AS-IntroVAE are able to generate stable and high-quality images. The posterior collapse problem is addressed by making per-batch attempts to transform the image so that it better fits the prior distribution in the latent space. Compared with the per-image approach, this strategy fosters more diverse distributions in the latent space, allowing our model to produce images of great diversity. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of AS-IntroVAE on image generation and reconstruction tasks.
AS-IntroVAE:对抗性相似距离产生稳健的IntroVAE
最近,IntroVAE和S-IntroVAE等内省模型在图像生成和重建任务中表现出色。内省模型的主要特征是VAE的对抗性学习,其中编码器试图区分真实和虚假(即合成)图像。然而,由于缺乏一种有效的度量来评估真假图像之间的差异,后验崩溃和梯度消失问题仍然存在,降低了合成图像的保真度。本文提出了一种新的内省变分自编码器——对抗相似距离内省变分自编码器(AS-IntroVAE)。我们从理论上分析了梯度消失问题,并利用2-Wasserstein距离和核技巧构造了一个新的对抗相似距离(AS-Distance)。通过对AS-Distance和KL-Divergence进行加权退火,AS-IntroVAE能够生成稳定的高质量图像。后验崩溃问题是通过逐批尝试变换图像,使其更好地适应潜在空间中的先验分布来解决的。与单图像方法相比,该策略在潜在空间中培养了更多样化的分布,使我们的模型能够产生具有极大多样性的图像。在基准数据集上的综合实验证明了AS-IntroVAE在图像生成和重建任务上的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信