中文
相关论文

相关论文: VAE^2: Preventing Posterior Collapse of Variationa…

200 篇论文

The posterior collapse phenomenon in variational autoencoder (VAE), where the variational posterior distribution closely matches the prior distribution, can hinder the quality of the learned latent variables. As a consequence of posterior…

机器学习 · 统计学 2024-05-14 Hien Dang , Tho Tran , Tan Nguyen , Nhat Ho

The variational autoencoder (VAE) is a popular combination of deep latent variable model and accompanying variational learning technique. By using a neural inference network to approximate the model's posterior on latent variables, VAEs…

机器学习 · 计算机科学 2019-01-30 Junxian He , Daniel Spokoyny , Graham Neubig , Taylor Berg-Kirkpatrick

Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Yazhou Xing , Yang Fei , Yingqing He , Jingye Chen , Jiaxin Xie , Xiaowei Chi , Qifeng Chen

Predicting the future in real-world settings, particularly from raw sensory observations such as images, is exceptionally challenging. Real-world events can be stochastic and unpredictable, and the high dimensionality and complexity of…

计算机视觉与模式识别 · 计算机科学 2018-03-07 Mohammad Babaeizadeh , Chelsea Finn , Dumitru Erhan , Roy H. Campbell , Sergey Levine

Variational autoencoders (VAEs) are a standard framework for inducing latent variable models that have been shown effective in learning text representations as well as in text generation. The key challenge with using VAEs is the {\it…

机器学习 · 计算机科学 2020-05-01 Serhii Havrylov , Ivan Titov

Multi-agent behavior modeling and trajectory forecasting are crucial for the safe navigation of autonomous agents in interactive scenarios. Variational Autoencoder (VAE) has been widely applied in multi-agent interaction modeling to…

机器学习 · 计算机科学 2021-12-02 Chen Tang , Wei Zhan , Masayoshi Tomizuka

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Yian Zhao , Feng Wang , Qiushan Guo , Chang Liu , Xiangyang Ji , Jian Zhang , Jie Chen

In recent years, the task of video prediction-forecasting future video given past video frames-has attracted attention in the research community. In this paper we propose a novel approach to this problem with Vector Quantized Variational…

计算机视觉与模式识别 · 计算机科学 2021-03-03 Jacob Walker , Ali Razavi , Aäron van den Oord

Variational auto-encoders (VAEs) are a popular and powerful deep generative model. Previous works on VAEs have assumed a factorized likelihood model, whereby the output uncertainty of each pixel is assumed to be independent. This…

机器学习 · 统计学 2026-05-14 Gara Dorta , Sara Vicente , Lourdes Agapito , Neill D. F. Campbell , Ivor Simpson

Variational language models seek to estimate the posterior of latent variables with an approximated variational posterior. The model often assumes the variational posterior to be factorized even when the true posterior is not. The learned…

计算与语言 · 计算机科学 2019-09-10 Prince Zizhuang Wang , William Yang Wang

Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to account for the…

机器学习 · 计算机科学 2020-04-20 Da Tang , Dawen Liang , Tony Jebara , Nicholas Ruozzi

The Variational Autoencoder (VAE) is known to suffer from the phenomenon of \textit{posterior collapse}, where the latent representations generated by the model become independent of the inputs. This leads to degenerated representations of…

机器学习 · 计算机科学 2023-09-12 Fotios Lygerakis , Elmar Rueckert

Variational autoencoders (VAEs) frequently suffer from posterior collapse, where the latent variables become uninformative as the approximate posterior degenerates to the prior. While recent work has characterized collapse as a phase…

机器学习 · 计算机科学 2026-05-19 Zegu Zhang , Jian Zhang

We investigate the phenomenon of posterior collapse in variational autoencoders (VAEs) from the perspective of statistical physics, and reveal that it constitutes a phase transition governed jointly by data structure and model…

机器学习 · 计算机科学 2025-12-25 Zhen Li , Fan Zhang , Zheng Zhang , Yu Chen

Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model…

计算机视觉与模式识别 · 计算机科学 2019-04-30 Lluis Castrejon , Nicolas Ballas , Aaron Courville

Variational autoencoders (VAEs) combine latent variables with amortized variational inference, whose optimization usually converges into a trivial local optimum termed posterior collapse, especially in text modeling. By tracking the…

计算与语言 · 计算机科学 2020-04-21 Chen Wu , Prince Zizhuang Wang , William Yang Wang

Variational autoencoders (VAEs) often suffer from posterior collapse, which is a phenomenon in which the learned latent space becomes uninformative. This is often related to the hyperparameter resembling the data variance. It can be shown…

机器学习 · 计算机科学 2022-08-23 Yuhta Takida , Wei-Hsiang Liao , Chieh-Hsin Lai , Toshimitsu Uesaka , Shusuke Takahashi , Yuki Mitsufuji

We introduce the task of action-driven stochastic human motion prediction, which aims to predict multiple plausible future motions given a sequence of action labels and a short motion history. This differs from existing works, which predict…

计算机视觉与模式识别 · 计算机科学 2022-06-01 Wei Mao , Miaomiao Liu , Mathieu Salzmann

Structured variational autoencoders (SVAEs) combine probabilistic graphical model priors on latent variables, deep neural networks to link latent variables to observed data, and structure-exploiting algorithms for approximate posterior…

机器学习 · 统计学 2023-05-29 Yixiu Zhao , Scott W. Linderman

As a general-purpose generative model architecture, VAE has been widely used in the field of image and natural language processing. VAE maps high dimensional sample data into continuous latent variables with unsupervised learning. Sampling…

机器学习 · 统计学 2019-11-05 Yao Li
‹ 上一页 1 2 3 10 下一页 ›