paper-with-me

홈 › Papers

Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning

2022-05-30 · Julian Burghoff, Robin Chan, Hanno Gottschalk, Annika Muetze, Tobias Riedlinger, Matthias Rottmann, Marius Schubert

Bringing deep neural networks (DNNs) into safety critical applications such as automated driving, medical imaging and finance, requires a thorough treatment of the model's uncertainties. Training deep neural networks is already resource demanding and so is also their uncertainty quantification. In this overview article, we survey methods that we developed to teach DNNs to be uncertain when they encounter new object classes. Additionally, we present training methods to learn from only a few labels with help of uncertainty quantification. Note that this is typically paid with a massive overhead in computation of an order of magnitude and more compared to ordinary network training. Finally, we survey our work on neural architecture search which is also an order of magnitude more resource demanding then ordinary network training.

📄 PDF Abstract BibTeX arXiv:2205.14917

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture SearchSurveyUncertainty Quantification

Similar Papers 제목 키워드 기반

Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation

2020-07-31 · Yichen Shen, Zhilu Zhang, Mert R. Sabuncu, Lin Sun

Calibrated estimates of uncertainty are critical for many real-world computer vision applications of deep learning. While there are several widely-used uncertainty estimation methods, dropout inference stands out for its…

Depth EstimationSemantic SegmentationUncertainty Quantification

I Find Your Lack of Uncertainty in Computer Vision Disturbing

2021-04-16 · Matias Valdenegro-Toro

Neural networks are used for many real world applications, but often they have problems estimating their own confidence. This is particularly problematic for computer vision applications aimed at making high stakes decis…

Out-of-Distribution DetectionUncertainty Quantification

Uncertainties of Latent Representations in Computer Vision

2024-08-26 · Michael Kirchhof

Uncertainty quantification is a key pillar of trustworthy machine learning. It enables safe reactions under unsafe inputs, like predicting only when the machine learning model detects sufficient evidence, discarding anom…

image-classificationImage ClassificationMedical Image ClassificationRepresentation Learning+2

Uncertainty Quantification for cross-subject Motor Imagery classification

2024-03-14 · Prithviraj Manivannan, Ivo Pascal de Jong, Matias Valdenegro-Toro, Andreea Ioana Sburlea

Uncertainty Quantification aims to determine when the prediction from a Machine Learning model is likely to be wrong. Computer Vision research has explored methods for determining epistemic uncertainty (also known as mod…

Brain Computer InterfaceClassificationMotor ImageryUncertainty Quantification

ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation

2021-04-14 · Martin Ferianc, Divyansh Manocha, Hongxiang Fan, Miguel Rodrigues

Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Pred…

Bayesian InferenceDecision MakingImage SegmentationSemantic Segmentation+1