中文
相关论文

相关论文: Variance Loss in Variational Autoencoders

200 篇论文

Variational Autoencoders (VAEs) have gained significant popularity among researchers as a powerful tool for understanding unknown distributions based on limited samples. This popularity stems partly from their impressive performance and…

机器学习 · 计算机科学 2024-02-27 Saptarshi Chakraborty , Peter L. Bartlett

Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, decoding a random latent vector from the prior usually does not produce meaningful data, at least…

机器学习 · 计算机科学 2025-07-23 Alejandro Ascarate , Leo Lebrat , Rodrigo Santa Cruz , Clinton Fookes , Olivier Salvado

We consider the task of estimating variational autoencoders (VAEs) when the training data is incomplete. We show that missing data increases the complexity of the model's posterior distribution over the latent variables compared to the…

机器学习 · 计算机科学 2024-06-28 Vaidotas Simkus , Michael U. Gutmann

VAE, or variational auto-encoder, compresses data into latent attributes, and generates new data of different varieties. VAE based on KL divergence has been considered as an effective technique for data augmentation. In this paper, we…

机器学习 · 计算机科学 2022-08-17 Zichuan Chen , Peng Liu

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

A new form of variational autoencoder (VAE) is developed, in which the joint distribution of data and codes is considered in two (symmetric) forms: ($i$) from observed data fed through the encoder to yield codes, and ($ii$) from latent…

机器学习 · 计算机科学 2017-11-21 Yunchen Pu , Weiyao Wang , Ricardo Henao , Liqun Chen , Zhe Gan , Chunyuan Li , Lawrence Carin

The Fr\'echet Video Distance (FVD) is a widely adopted metric for evaluating video generation distribution quality. However, its effectiveness relies on critical assumptions. Our analysis reveals three significant limitations: (1) the…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Ge Ya Luo , Gian Mario Favero , Zhi Hao Luo , Alexia Jolicoeur-Martineau , Christopher Pal

This work presents an analysis of the hidden representations of Variational Autoencoders (VAEs) using the Intrinsic Dimension (ID) and the Information Imbalance (II). We show that VAEs undergo a transition in behaviour once the bottleneck…

机器学习 · 计算机科学 2024-11-05 Charles Camboulin , Diego Doimo , Aldo Glielmo

Sampling trajectories from a distribution followed by ranking them based on a specified cost function is a common approach in autonomous driving. Typically, the sampling distribution is hand-crafted (e.g a Gaussian, or a grid). Recently,…

机器人学 · 计算机科学 2024-04-26 Simon Idoko , Basant Sharma , Arun Kumar Singh

Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges,…

数据分析、统计与概率 · 物理学 2025-08-18 Alexander Yue , Haoyi Jia , Julia Gonski

Variational Autoencoders (VAEs) were originally motivated (Kingma & Welling, 2014) as probabilistic generative models in which one performs approximate Bayesian inference. The proposal of $\beta$-VAEs (Higgins et al., 2017) breaks this…

机器学习 · 统计学 2023-02-10 Tim Z. Xiao , Robert Bamler

The generation of discontinuous distributions is a difficult task for most known frameworks such as generative autoencoders and generative adversarial networks. Generative non-invertible models are unable to accurately generate such…

机器学习 · 计算机科学 2021-12-20 Mariia Drozdova , Vitaliy Kinakh , Guillaume Quétant , Tobias Golling , Slava Voloshynovskiy

The variational autoencoder (VAE) is a popular, deep, latent-variable model (DLVM) due to its simple yet effective formulation for modeling the data distribution. Moreover, optimizing the VAE objective function is more manageable than other…

机器学习 · 计算机科学 2025-01-28 Surojit Saha , Sarang Joshi , Ross Whitaker

Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in…

机器学习 · 计算机科学 2023-12-13 Julia Huiming Wang , Dexter Tsin , Tatiana Engel

Variational autoencoders (VAEs) are one class of generative probabilistic latent-variable models designed for inference based on known data. We develop three variations on VAEs by introducing a second parameterized encoder/decoder pair and,…

机器学习 · 计算机科学 2023-04-06 R. I. Cukier

Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of lossy image compression from the perspective of generative…

图像与视频处理 · 电气工程与系统科学 2023-03-28 Zhihao Duan , Ming Lu , Zhan Ma , Fengqing Zhu

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…

Recent audio generation models typically rely on Variational Autoencoders (VAEs) and perform generation within the VAE latent space. Although VAEs excel at compression and reconstruction, their latents inherently encode low-level acoustic…

声音 · 计算机科学 2026-02-27 Zeyu Xie , Chenxing Li , Qiao Jin , Xuenan Xu , Guanrou Yang , Wenfu Wang , Mengyue Wu , Dong Yu , Yuexian Zou

We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input…

计算与语言 · 计算机科学 2018-11-02 Yijun Xiao , Tiancheng Zhao , William Yang Wang

The success of deep learning-based generative models in producing realistic images, videos, and audios has led to a crucial consideration: how to effectively assess the quality of synthetic samples. While the Fr\'{e}chet Inception Distance…

机器学习 · 计算机科学 2024-03-12 Yang Chen , Dustin J. Kempton , Rafal A. Angryk