Robust outlier detection by de-biasing VAE likelihoods

TL;DR

This paper introduces bias correction methods for VAE likelihoods to improve outlier detection, achieving state-of-the-art results across multiple image datasets with computational efficiency.

Contribution

It proposes novel, sample-specific bias correction techniques for VAE likelihoods and demonstrates their effectiveness combined with contrast stretching for robust outlier detection.

Findings

Achieves state-of-the-art outlier detection accuracy on nine image datasets.

Bias correction methods are computationally inexpensive and effective.

Contrast stretching enhances the bias correction's performance.

Abstract

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 (DGMs) are a candidate metric for outlier detection with unlabeled data. Yet, previous studies have shown that DGM 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 of DGMs. We propose novel analytical and algorithmic approaches to ameliorate key biases with VAE likelihoods. Our bias corrections are sample-specific, computationally inexpensive, and readily computed for various decoder visible distributions. Next, we show that a well-known image pre-processing technique -- contrast stretching -- extends the effectiveness of bias correction to further improve outlier detection. Our approach achieves state-of-the-art accuracies with nine grayscale and natural image datasets, and demonstrates significant advantages -- both with speed and performance -- over four recent, competing approaches. In summary, lightweight remedies suffice to achieve robust outlier detection with VAEs.