Lipschitz Constrained Neural Networks for Robust Object Detection at Sea

Research output: Contribution to journalConference articleResearchpeer-review

23 Downloads (Pure)

Abstract

Autonomous ships relies on sensory data to perceive other objects of interest in their environment. Deep Learning based object detection in the image domain is a common approach to solve this issue. The robustness of such approaches in non-ideal conditions is, however, still to be proven. In this work state of the art methods are applied on the RetinaNet architecture attempting to create a more robust object detection network given noisy input data. The GroupSort activation function and Spectral Normalization is used and the results are compared to the standard RetinaNet network. Our findings show that these modifications perform better and ensure robustness under moderate noise levels, than the standard RetinaNet network.
Original languageEnglish
Article number012023
JournalIOP Conference Series: Materials Science and Engineering
Volume929
Number of pages11
ISSN1757-8981
DOIs
Publication statusPublished - 2020
Event3rd International Conference on Maritime Autonomous Surface Ship - Virtual event, Ulsan, Korea, Republic of
Duration: 11 Nov 202012 Nov 2020
Conference number: ICMASS 2020
https://www.icmass-conf.org/

Conference

Conference3rd International Conference on Maritime Autonomous Surface Ship
NumberICMASS 2020
LocationVirtual event
CountryKorea, Republic of
CityUlsan
Period11/11/202012/11/2020
Internet address

Fingerprint Dive into the research topics of 'Lipschitz Constrained Neural Networks for Robust Object Detection at Sea'. Together they form a unique fingerprint.

Cite this