paper-with-me

홈 › Papers

Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detection

2021-07-28 · Bang Xiang Yong, Tim Pearce, Alexandra Brintrup

After an autoencoder (AE) has learnt to reconstruct one dataset, it might be expected that the likelihood on an out-of-distribution (OOD) input would be low. This has been studied as an approach to detect OOD inputs. Recent work showed this intuitive approach can fail for the dataset pairs FashionMNIST vs MNIST. This paper suggests this is due to the use of Bernoulli likelihood and analyses why this is the case, proposing two fixes: 1) Compute the uncertainty of likelihood estimate by using a Bayesian version of the AE. 2) Use alternative distributions to model the likelihood.

📄 PDF Abstract BibTeX arXiv:2107.13304

Code (1)

bangxiangyong/bae-ood-images 공식 구현 pytorch

Tasks

Out-of-Distribution Detection

Methods 이 논문이 사용한 방법론

AE An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation…

Similar Papers 제목 키워드 기반

The continuous Bernoulli: fixing a pervasive error in variational autoencoders

2019-07-16 · NeurIPS 2019 12 · Gabriel Loaiza-Ganem, John P. Cunningham

Variational autoencoders (VAE) have quickly become a central tool in machine learning, applicable to a broad range of data types and latent variable models. By far the most common first step, taken by seminal papers and …

Labeled Multi-Bernoulli Tracking for Industrial Mobile Platform Safety

2016-04-20 · Tharindu Rathnayake, Reza Hoseinnezhad, Ruwan Tennakoon, Alireza Bab-Hadiashar

This paper presents a track-before-detect labeled multi-Bernoulli filter tailored for industrial mobile platform safety applications. We derive two application specific separable likelihood functions that capture the geo…

Gaussian Imagination in Bandit Learning

2022-01-06 · Yueyang Liu, Adithya M. Devraj, Benjamin Van Roy, Kuang Xu

Assuming distributions are Gaussian often facilitates computations that are otherwise intractable. We study the performance of an agent that attains a bounded information ratio with respect to a bandit environment with a…

Bayesian Beta-Bernoulli Process Sparse Coding with Deep Neural Networks

2023-03-14 · Arunesh Mittal, Kai Yang, Paul Sajda, John Paisley

Several approximate inference methods have been proposed for deep discrete latent variable models. However, non-parametric methods which have previously been successfully employed for classical sparse coding models have …

A Sufficient Statistics Construction of Bayesian Nonparametric Exponential Family Conjugate Models

2016-01-10 · Robert Finn, Brian Kulis

Conjugate pairs of distributions over infinite dimensional spaces are prominent in statistical learning theory, particularly due to the widespread adoption of Bayesian nonparametric methodologies for a host of models and…

Learning Theory