Unsupervised Out-of-Distribution Detection by Restoring Lossy Inputs with Variational Autoencoder
This addresses a critical issue in machine learning for ensuring model reliability in real-world applications, though it is an incremental improvement specific to VAEs.
The paper tackles the problem of unsupervised out-of-distribution detection, where deep generative models often fail by assigning higher likelihoods to OOD samples, and proposes a novel VAE-based score called Error Reduction that improves detection performance, as demonstrated through experiments on various datasets.
Deep generative models have been demonstrated as problematic in the unsupervised out-of-distribution (OOD) detection task, where they tend to assign higher likelihoods to OOD samples. Previous studies on this issue are usually not applicable to the Variational Autoencoder (VAE). As a popular subclass of generative models, the VAE can be effective with a relatively smaller model size and be more stable and faster in training and inference, which can be more advantageous in real-world applications. In this paper, We propose a novel VAE-based score called Error Reduction (ER) for OOD detection, which is based on a VAE that takes a lossy version of the training set as inputs and the original set as targets. Experiments are carried out on various datasets to show the effectiveness of our method, we also present the effect of design choices with ablation experiments. Our code is available at: https://github.com/ZJLAB-AMMI/VAE4OOD.