Searching for rare traffic signs

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/304032
Download file(s):
File Description SizeFormat 
master_thesis_Hannes_Gustafsson.pdf2.49 MBAdobe PDFView/Open
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGustafsson, Hannes-
dc.contributor.departmentChalmers tekniska högskola / Institutionen för fysiksv
dc.date.accessioned2021-09-02T11:26:40Z-
dc.date.available2021-09-02T11:26:40Z-
dc.date.issued2021sv
dc.date.submitted2020-
dc.identifier.urihttps://hdl.handle.net/20.500.12380/304032-
dc.description.abstractDeep neural networks are good at recognizing traffic signs when they are trained on many different examples of each one. However, some traffic signs are very rare and not often encountered when collecting data. This means that a network does not recognize rare traffic signs as well as those that are encountered often. When collecting large amounts of data, one usually only labels a small subset of it. Therefore, there might exist more examples of the rare traffic signs in the unlabeled data set. If these examples could be found and used in training, the performance of the model could be expected to improve. This thesis evaluates how a standard neural network performs in searching for rare traffic signs, and whether some commonly used techniques from few-shot learning can improve its performance. To our surprise we find that they cannot. Furthermore, in this thesis we show that searching for rare traffic signs is an efficient active learning method, outperforming other established methods by requiring up to 8x less additional data to achieve the same F1-score on rare traffic sign recognition.sv
dc.language.isoengsv
dc.setspec.uppsokPhysicsChemistryMaths-
dc.subjectComputersv
dc.subjectsciencesv
dc.subjectcomputer sciencesv
dc.subjectengineeringsv
dc.subjectprojectsv
dc.subjectthesissv
dc.subjectdeep learningsv
dc.titleSearching for rare traffic signssv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH-
dc.contributor.examinerMehlig, Bernhard-
dc.contributor.supervisorMehlig, Bernhard-
dc.identifier.coursecodeTIFX05sv
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.