Reweighting neural network examples for robust object detection at sea

Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of needing large amounts of annotated training data. Furthermore, the possibility of neural networks overfitting to the biases and faults included in th...

Full description

Saved in:
Bibliographic Details
Published inElectronics letters Vol. 57; no. 16; pp. 608 - 610
Main Authors Becktor, J., Boukas, E., Blanke, M., Nalpantidis, L.
Format Journal Article
LanguageEnglish
Published Stevenage John Wiley & Sons, Inc 01.08.2021
Wiley
Subjects
Annotations
Artificial neural networks
Computer vision and image processing techniques
Datasets
Fault detection
Fault tolerance
Neural nets
Neural networks
Object recognition
Optical, image and video signal processing
Robustness
Visual tasks
Online AccessGet full text

Cover

More Information
Summary:Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of needing large amounts of annotated training data. Furthermore, the possibility of neural networks overfitting to the biases and faults included in their respective datasets. In this work, methods for achieving robust neural networks, able to tolerate untrusted and possibly erroneous training data, are explored. The proposed method is shown to improve performance and help neural networks learn from untrusted data, provided a thoroughly annotated subset.
ISSN:0013-5194
1350-911X
DOI:10.1049/ell2.12166