Open AccessReweighting neural network examples for robust object detection at sea
Author(s) -
Becktor J.,
Boukas E.,
Blanke M.,
Nalpantidis L.
Publication year - 2021
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/ell2.12166
Subject(s) - overfitting , computer science , artificial neural network , artificial intelligence , deep neural networks , object (grammar) , machine learning , deep learning , training set , object detection , time delay neural network , data mining , pattern recognition (psychology)
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.