Evaluation of Self-Supervised Learning for Vehicle-Type Detection in Autonomous Driving

Ahmed, Manaf

dc.contributor.advisor	Glauner, Patrick
dc.contributor.author	Ahmed, Manaf
dc.date.accessioned	2026-01-06T11:55:32Z
dc.date.available	2026-01-06T11:55:32Z
dc.date.issued	2023
dc.date.submitted	2023-08-31
dc.identifier.uri	https://dspace.jcu.cz/handle/20.500.14390/48682
dc.description.abstract	Self-Supervised Learning (SSL) method was implemented on vehicle-type detection task within autonomous driving context. The task involved evaluation of prominent SSL methods such as SimCLR and SimSiam against the conventional supervised method. The study explores the influence of different factors on the performance of SSL and its ability to generalize well under different circumstances.	cze
dc.format	68 p. (111 408 characters)
dc.format	68 p. (111 408 characters)
dc.language.iso	eng
dc.publisher	Jihočeská univerzita	cze
dc.rights	Bez omezení
dc.subject	Self-Supervised Learning	cze
dc.subject	Object Detection	cze
dc.subject	Vehicle-type	cze
dc.subject	SimSiam	cze
dc.subject	SimCLR	cze
dc.subject	Autonomous Driving	cze
dc.subject	Contrastive Learning	cze
dc.subject	Self-Supervised Learning	eng
dc.subject	Object Detection	eng
dc.subject	Vehicle-type	eng
dc.subject	SimSiam	eng
dc.subject	SimCLR	eng
dc.subject	Autonomous Driving	eng
dc.subject	Contrastive Learning	eng
dc.title	Evaluation of Self-Supervised Learning for Vehicle-Type Detection in Autonomous Driving	cze
dc.title.alternative	Evaluation of Self-Supervised Learning for Vehicle-Type Detection in Autonomous Driving	eng
dc.type	diplomová práce	cze
dc.identifier.stag	73276
dc.description.abstract-translated	Self-Supervised Learning (SSL) method was implemented on vehicle-type detection task within autonomous driving context. The task involved evaluation of prominent SSL methods such as SimCLR and SimSiam against the conventional supervised method. The study explores the influence of different factors on the performance of SSL and its ability to generalize well under different circumstances.	eng
dc.date.accepted	2023-09-20
dc.description.department	Přírodovědecká fakulta	cze
dc.thesis.degree-discipline	Artificial Intelligence and Data Science	cze
dc.thesis.degree-grantor	Jihočeská univerzita. Přírodovědecká fakulta	cze
dc.thesis.degree-name	Mgr.
dc.thesis.degree-program	Artificial Intelligence and Data Science	cze
dc.description.grade	Dokončená práce s úspěšnou obhajobou	cze
dc.contributor.referee	Mayer, Markus
dc.contributor.referee	Torkler, Phillipp
dc.description.defence	<p>Komise: Valdman (chairman), Předota, Bukovský, Berl, Torkler, Prokýšek, Budík, Geyer</p> <p>The student presented his work in time. His speech was clear and very easy to understand.</p> <p>Did you split the training dataset?</p> <p> </p>	cze