A Variational Dirichlet Framework for Out-of-Distribution Detection

Abstract

With the recently rapid development in deep learning, deep neural networks have been widely adopted in many real-life applications. However, deep neural networks are also known to have very little control over its uncertainty for unseen examples, which potentially causes very harmful and annoying consequences in practical scenarios. In this paper, we are particularly interested in designing a higher-order uncertainty metric for deep neural networks and investigate its effectiveness under the out-of-distribution detection task proposed by~\cite{hendrycks2016baseline}. Our method first assumes there exists an underlying higher-order distribution $\mathbb{P}(z)$, which controls label-wise categorical distribution $\mathbb{P}(y)$ over classes on the K-dimension simplex, and then approximate such higher-order distribution via parameterized posterior function $p_{\theta }(z|x)$ under variational inference framework, finally we use the entropy of learned posterior distribution $p_{\theta }(z|x)$ as uncertainty measure to detect out-of-distribution examples. Further, we propose an auxiliary objective function to discriminate against synthesized adversarial examples to further increase the robustness of the proposed uncertainty measure. Through comprehensive experiments on various datasets, our proposed framework is demonstrated to consistently outperform competing algorithms.

arXiv commentTech Report

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Estimation of Word Representations in Vector Space
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Achieving Human Parity on Automatic Chinese to English News Translation
• Evidential Deep Learning to Quantify Classification Uncertainty
• Regularizing Neural Networks by Penalizing Confident Output Distributions
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Bayesian Dark Knowledge
• Variational Reasoning for Question Answering with Knowledge Graph
• Triangular Architecture for Rare Language Translation

Cited by in corpus (8)

• Contrastive Training for Improved Out-of-Distribution Detection
• Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
• Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
• TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring
• Deep Evidential Regression
• Being Bayesian about Categorical Probability
• Combining Model and Parameter Uncertainty in Bayesian Neural Networks
• Dirichlet uncertainty wrappers for actionable algorithm accuracy accountability and auditability