paper-with-me

홈 › Papers

Feature Map Variational Auto-Encoders

2018-01-01 · ICLR 2018 1 · Lars Maaløe, Ole Winther

There have been multiple attempts with variational auto-encoders (VAE) to learn powerful global representations of complex data using a combination of latent stochastic variables and an autoregressive model over the dimensions of the data. However, for the most challenging natural image tasks the purely autoregressive model with stochastic variables still outperform the combined stochastic autoregressive models. In this paper, we present simple additions to the VAE framework that generalize to natural images by embedding spatial information in the stochastic layers. We significantly improve the state-of-the-art results on MNIST, OMNIGLOT, CIFAR10 and ImageNet when the feature map parameterization of the stochastic variables are combined with the autoregressive PixelCNN approach. Interestingly, we also observe close to state-of-the-art results without the autoregressive part. This opens the possibility for high quality image generation with only one forward-pass.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

PixelCNN A PixelCNN is a generative model that uses autoregressive connections to model images pixel by pixel, decomposing the joint image distribution as a product of conditionals.…
USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

The advantage of using Student's t-priors in variational autoencoders

2019-09-25 · Najmeh Abiri, Mattias Ohlsson

Is it optimal to use the standard Gaussian prior in variational autoencoders? With Gaussian distributions, which are not weakly informative priors, variational autoencoders struggle to reconstruct the actual data. We pro…

Factorized Gaussian Process Variational Autoencoders

2020-11-14 · pproximateinference AABI Symposium 2021 1 · Metod Jazbec, Michael Pearce, Vincent Fortuin

Variational autoencoders often assume isotropic Gaussian priors and mean-field posteriors, hence do not exploit structure in scenarios where we may expect similarity or consistency across latent variables. Gaussian proce…

An Introduction to Variational Autoencoders

2019-06-06 · Diederik P. Kingma, Max Welling

Variational autoencoders provide a principled framework for learning deep latent-variable models and corresponding inference models. In this work, we provide an introduction to variational autoencoders and some important…

DoS and DDoS Mitigation Using Variational Autoencoders

2021-05-14 · Eirik Molde Bårli, Anis Yazidi, Enrique Herrera Viedma, Hårek Haugerud

DoS and DDoS attacks have been growing in size and number over the last decade and existing solutions to mitigate these attacks are in general inefficient. Compared to other types of malicious cyber attacks, DoS and DDoS…

Anomaly Detection

SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders

2024-07-18 · Sheng-Wei Li, Zi-Xiang Wei, Wei-Jie Chen, Yi-Hsin Yu 외

Existing zero-shot skeleton-based action recognition methods utilize projection networks to learn a shared latent space of skeleton features and semantic embeddings. The inherent imbalance in action recognition datasets,…

Action RecognitionDisentanglementGeneralized Zero Shot skeletal action recognitionSkeleton Based Action Recognition+2