paper-with-me

Papers

Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation

2020-05-21 · Hong Joo Lee, Seong Tae Kim, Hakmin Lee, Nassir Navab, Yong Man Ro

Recent studies have shown that ensemble approaches could not only improve accuracy and but also estimate model uncertainty in deep learning. However, it requires a large number of parameters according to the increase of ensemble models for better prediction and uncertainty estimation. To address this issue, a generic and efficient segmentation framework to construct ensemble segmentation models is devised in this paper. In the proposed method, ensemble models can be efficiently generated by using the stochastic layer selection method. The ensemble models are trained to estimate uncertainty through Bayesian approximation. Moreover, to overcome its limitation from uncertain instances, we devise a new pixel-wise uncertainty loss, which improves the predictive performance. To evaluate our method, comprehensive and comparative experiments have been conducted on two datasets. Experimental results show that the proposed method could provide useful uncertainty information by Bayesian approximation with the efficient ensemble model generation and improve the predictive performance.

📄 PDF Abstract BibTeX arXiv:2005.10754

Code (0)

등록된 구현이 없습니다.

Tasks

Segmentation

Similar Papers 제목 키워드 기반

Can Bayesian Neural Networks Explicitly Model Input Uncertainty?

2025-01-14 · Matias Valdenegro-Toro, Marco Zullich

Inputs to machine learning models can have associated noise or uncertainties, but they are often ignored and not modelled. It is unknown if Bayesian Neural Networks and their approximations are able to consider uncertain…

model

Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification

2019-10-17 · Matias Valdenegro-Toro

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. …

ClassificationGeneral Classificationimage-classificationImage Classification

Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation

2020-06-13 · Zhiyun Lu, Eugene Ie, Fei Sha

Many methods have been proposed to quantify the predictive uncertainty associated with the outputs of deep neural networks. Among them, ensemble methods often lead to state-of-the-art results, though they require modific…

Out-of-Distribution Detection

Deep Ensembles from a Bayesian Perspective

2021-05-27 · Lara Hoffmann, Clemens Elster

Deep ensembles can be considered as the current state-of-the-art for uncertainty quantification in deep learning. While the approach was originally proposed as a non-Bayesian technique, arguments supporting its Bayesian …

Uncertainty Quantification

Variance-Gated Ensembles: An Epistemic-Aware Framework for Uncertainty Estimation

2026-02-08 · H. Martin Gillis, Isaac Xu, Thomas Trappenberg arxiv

Machine learning applications require fast and reliable per-sample uncertainty estimation. A common approach is to use predictive distributions from Bayesian or approximation methods and additively decompose uncertainty …