Optimistic and pessimistic neural networks for object recognition

In this paper the application of uncertainty modeling to convolutional neural networks is evaluated. A novel method for adjusting the network's predictions based on uncertainty information is introduced. This allows the network to be either optimistic or pessimistic in it's prediction scor...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE International Conference on Image Processing (ICIP) pp. 350 - 354
Main Authors Grzeszick, Rene, Sudholt, Sebastian, Fink, Gernot A.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2017
Subjects
Biological neural networks
Computational modeling
Deep Neural Networks
Dropout
Neurons
Output Modeling
Predictive models
Task analysis
Training
Uncertainty
Online AccessGet full text

Cover

More Information
Summary:In this paper the application of uncertainty modeling to convolutional neural networks is evaluated. A novel method for adjusting the network's predictions based on uncertainty information is introduced. This allows the network to be either optimistic or pessimistic in it's prediction scores. The proposed method builds on the idea of applying dropout at test time and sampling a predictive mean and variance from the network's output. Besides the methodological aspects, implementation details allowing for a fast evaluation are presented. In the evaluation on the ILSVRC2014 and VOC2011 datasets it will be shown that modeling uncertainty allows for improving the performance of a given model purely at test time without any further training steps.
ISSN:2381-8549
DOI:10.1109/ICIP.2017.8296301