Detecting out-of-distribution samples via variational auto-encoder with reliable uncertainty estimation. (January 2022)

• Record Type: Journal Article
• Authors: Ran, Xuming; Xu, Mingkun; Mei, Lingrui; Xu, Qi; Liu, Quanying
• Is Part Of: Neural networks. Volume 145(2022)
• Page Start: 199
• Page End: 208
• Publication Date: 2022-01
• Subjects: Variational auto-encoder -- Out-of-distribution detection -- Uncertainty estimation -- Noise contrastive prior; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.10.020
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Variational autoencoders (VAEs) are influential generative models with rich representation capabilities from the deep neural network architecture and Bayesian method. However, VAE models have a weakness that assign a higher likelihood to out-of-distribution (OOD) inputs than in-distribution (ID) inputs. To address this problem, a reliable uncertainty estimation is considered to be critical for in-depth understanding of OOD inputs. In this study, we propose an improved noise contrastive prior (INCP) to be able to integrate into the encoder of VAEs, called INCPVAE. INCP is scalable, trainable and compatible with VAEs, and it also adopts the merits from the INCP for uncertainty estimation. Experiments on various datasets demonstrate that compared to the standard VAEs, our model is superior in uncertainty estimation for the OOD data and is robust in anomaly detection tasks. The INCPVAE model obtains reliable uncertainty estimation for OOD inputs and solves the OOD problem in VAE models.