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

10/05/2020
by   Omer Achrack, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/17/2019

Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification

Fast estimates of model uncertainty are required for many robust robotic...
research
06/17/2020

Sample Efficient Uncertainty Estimation for Deep Learning Safety

Deep Neural Networks (DNNs) are known to make highly overconfident predi...
research
06/07/2019

DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks

Deep neural networks (DNNs) have achieved state-of-the-art performances ...
research
03/17/2023

DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation

Deep neural networks lack interpretability and tend to be overconfident,...
research
05/28/2021

Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving

In this paper, we show how uncertainty estimation can be leveraged to en...
research
02/11/2021

The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms

Neural networks (NNs) lack measures of "reliability" estimation that wou...
research
03/29/2020

SuperNet – An efficient method of neural networks ensembling

The main flaw of neural network ensembling is that it is exceptionally d...

Please sign up or login with your details

Forgot password? Click here to reset