Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification
Fast estimates of model uncertainty are required for many robust robotics applications. Deep Ensembles provides state of the art uncertainty without requiring Bayesian methods, but still it is computationally expensive. In this paper we propose deep sub-ensembles, an approximation to deep ensembles where the core idea is to ensemble only the layers close to the output, and not the whole model. With ResNet-20 on the CIFAR10 dataset, we obtain 1.5-2.5 speedup over a Deep Ensemble, with a small increase in error and NLL, and similarly up to 5-15 speedup with a VGG-like network on the SVHN dataset. Our results show that this idea enables a trade-off between error and uncertainty quality versus computational performance.
Code (2)
Tasks
ClassificationGeneral Classificationimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Fast and reliable uncertainty quantification with neural network ensembles for industrial image classification
Image classification with neural networks (NNs) is widely used in industrial processes, situations where the model likely encounters unknown objects during deployment, i.e., out-of-distribution (OOD) data. Worryingly, NN…
Diversityimage-classificationImage ClassificationUncertainty QuantificationLiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection
The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty…
3D Object DetectionObjectobject-detectionObject DetectionBenchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise
In the past years, deep learning has seen an increase in usage in the domain of histopathological applications. However, while these approaches have shown great potential, in high-risk environments deep learning models n…
BenchmarkingClassificationData AugmentationVariational Inference+1Quantum parameter estimation with uncertainty quantification from continuous measurement data using neural network ensembles
We show that ensembles of deep neural networks, called deep ensembles, can be used to perform quantum parameter estimation while also providing a means for quantifying uncertainty in parameter estimates, which is a key a…
Bayesian InferenceWindow-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models
Deep Ensembles are a simple, reliable, and effective method of improving both the predictive performance and uncertainty estimates of deep learning approaches. However, they are widely criticised as being computationally…
Binary Classification