Deep Evidential Regression

Abstract

Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust, and efficient measures of uncertainty are crucial. In this paper, we propose a novel method for training non-Bayesian NNs to estimate a continuous target as well as its associated evidence in order to learn both aleatoric and epistemic uncertainty. We accomplish this by placing evidential priors over the original Gaussian likelihood function and training the NN to infer the hyperparameters of the evidential distribution. We additionally impose priors during training such that the model is regularized when its predicted evidence is not aligned with the correct output. Our method does not rely on sampling during inference or on out-of-distribution (OOD) examples for training, thus enabling efficient and scalable uncertainty learning. We demonstrate learning well-calibrated measures of uncertainty on various benchmarks, scaling to complex computer vision tasks, as well as robustness to adversarial and OOD test samples.

Code available on: https://github.com/aamini/evidential-deep-learning

References in corpus (19)

• LSTM: A Search Space Odyssey
• End to End Learning for Self-Driving Cars
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Weight Uncertainty in Neural Networks
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Evidential Deep Learning to Quantify Classification Uncertainty
• Variational Dropout and the Local Reparameterization Trick
• Accurate Uncertainties for Deep Learning Using Calibrated Regression
• Variational Dropout Sparsifies Deep Neural Networks
• Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
• Variational End-to-End Navigation and Localization
• Reliable Prediction Intervals with Regression Neural Networks
• Noise Contrastive Priors for Functional Uncertainty
• The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models
• Information Aware Max-Norm Dirichlet Networks for Predictive Uncertainty Estimation
• Kullback-Leibler Divergence for the Normal-Gamma Distribution
• Spatial Uncertainty Sampling for End-to-End Control
• A Variational Dirichlet Framework for Out-of-Distribution Detection
• Being Bayesian about Categorical Probability

Cited by in corpus (5)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• GoTube: Scalable Stochastic Verification of Continuous-Depth Models
• Continuous Monitoring of Blood Pressure with Evidential Regression
• StelNet: Hierarchical Neural Network for Automatic Inference in Stellar Characterization
• Low-Regret Active learning