Multi-Loss Sub-Ensembles for Accurate Classification with Uncertainty Estimation

Abstract

Deep neural networks (DNNs) have made a revolution in numerous fields during the last decade. However, in tasks with high safety requirements, such as medical or autonomous driving applications, providing an assessment of the models reliability can be vital. Uncertainty estimation for DNNs has been addressed using Bayesian methods, providing mathematically founded models for reliability assessment. These model are computationally expensive and generally impractical for many real-time use cases. Recently, non-Bayesian methods were proposed to tackle uncertainty estimation more efficiently. We propose an efficient method for uncertainty estimation in DNNs achieving high accuracy. We simulate the notion of multi-task learning on single-task problems by producing parallel predictions from similar models differing by their loss. This multi-loss approach allows one-phase training for single-task learning with uncertainty estimation. We keep our inference time relatively low by leveraging the advantage proposed by the Deep-Sub-Ensembles method. The novelty of this work resides in the proposed accurate variational inference with a simple and convenient training procedure, while remaining competitive in terms of computational time. We conduct experiments on SVHN, CIFAR10, CIFAR100 as well as Image-Net using different architectures. Our results show improved accuracy on the classification task and competitive results on several uncertainty measures.

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Improving neural networks by preventing co-adaptation of feature detectors
• An overview of gradient descent optimization algorithms
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Weight Uncertainty in Neural Networks
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Evidential Deep Learning to Quantify Classification Uncertainty
• DropBlock: A regularization method for convolutional networks
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
• Single-Model Uncertainties for Deep Learning
• Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
• Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
• Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
• Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks
• Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification
• DropCluster: A structured dropout for convolutional networks