Efficient remedies for outlier detection with variational autoencoders

08/19/2021
by   Kushal Chauhan, et al.
8

Deep networks often make confident, yet incorrect, predictions when tested with outlier data that is far removed from their training distributions. Likelihoods computed by deep generative models are a candidate metric for outlier detection with unlabeled data. Yet, previous studies have shown that such likelihoods are unreliable and can be easily biased by simple transformations to input data. Here, we examine outlier detection with variational autoencoders (VAEs), among the simplest class of deep generative models. First, we show that a theoretically-grounded correction readily ameliorates a key bias with VAE likelihood estimates. The bias correction is model-free, sample-specific, and accurately computed with the Bernoulli and continuous Bernoulli visible distributions. Second, we show that a well-known preprocessing technique, contrast normalization, extends the effectiveness of bias correction to natural image datasets. Third, we show that the variance of the likelihoods computed over an ensemble of VAEs also enables robust outlier detection. We perform a comprehensive evaluation of our remedies with nine (grayscale and natural) image datasets, and demonstrate significant advantages, in terms of both speed and accuracy, over four other state-of-the-art methods. Our lightweight remedies are biologically inspired and may serve to achieve efficient outlier detection with many types of deep generative models.

READ FULL TEXT

page 2

page 7

page 16

page 23

research
08/29/2022

Shaken, and Stirred: Long-Range Dependencies Enable Robust Outlier Detection with PixelCNN++

Reliable outlier detection is critical for real-world applications of de...
research
06/15/2021

Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models

Out-of-distribution (OOD) detection is an important task in machine lear...
research
07/15/2019

Robust Variational Autoencoders for Outlier Detection in Mixed-Type Data

We focus on the problem of unsupervised cell outlier detection in mixed ...
research
11/12/2019

Deep Variational Semi-Supervised Novelty Detection

In anomaly detection (AD), one seeks to identify whether a test sample i...
research
06/23/2019

Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting

A learned generative model often produces biased statistics relative to ...
research
10/25/2020

Further Analysis of Outlier Detection with Deep Generative Models

The recent, counter-intuitive discovery that deep generative models (DGM...
research
03/01/2018

Modeling Data Containing Outliers using ARIMA Additive Outlier (ARIMA-AO)

The aim this study is discussed on the detection and correction of data ...

Please sign up or login with your details

Forgot password? Click here to reset