paper-with-me

Papers

Inverting Variational Autoencoders for Improved Generative Accuracy

2016-08-21 · Ian Gemp, Ishan Durugkar, Mario Parente, M. Darby Dyar, Sridhar Mahadevan

Recent advances in semi-supervised learning with deep generative models have shown promise in generalizing from small labeled datasets ($\mathbf{x},\mathbf{y}$) to large unlabeled ones ($\mathbf{x}$). In the case where the codomain has known structure, a large unfeatured dataset ($\mathbf{y}$) is potentially available. We develop a parameter-efficient, deep semi-supervised generative model for the purpose of exploiting this untapped data source. Empirical results show improved performance in disentangling latent variable semantics as well as improved discriminative prediction on Martian spectroscopic and handwritten digit domains.

📄 PDF Abstract BibTeX arXiv:1608.05983

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Modeling Barrett's Esophagus Progression using Geometric Variational Autoencoders

2023-03-17 · Vivien van Veldhuizen, Sharvaree Vadgama, Onno J. de Boer, Sybren Meijer 외

Early detection of Barrett's Esophagus (BE), the only known precursor to Esophageal adenocarcinoma (EAC), is crucial for effectively preventing and treating esophageal cancer. In this work, we investigate the potential o…

PrognosisRepresentation Learning

Learning variational autoencoders via MCMC speed measures

2023-08-26 · Marcel Hirt, Vasileios Kreouzis, Petros Dellaportas

Variational autoencoders (VAEs) are popular likelihood-based generative models which can be efficiently trained by maximizing an Evidence Lower Bound (ELBO). There has been much progress in improving the expressiveness o…

Training Variational Autoencoders with Buffered Stochastic Variational Inference

2019-02-27 · Rui Shu, Hung H. Bui, Jay Whang, Stefano Ermon

The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this techni…

Variational Inference

Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders

2024-02-01 · Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann 외

Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explaine…

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

2017-01-17 · ICML 2017 8 · Lars Mescheder, Sebastian Nowozin, Andreas Geiger

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 ex…