Show simple item record

dc.contributor.authorAngus, Matt 18:26:48 (GMT) 18:26:48 (GMT)
dc.description.abstractThere exists wide research surrounding the detection of out of distribution sample for image classification. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing an image to be out of distribution. This thesis adapts state-of-the-art methods for detecting out of distribution images for image classification to the new task of detecting out of distribution pixels, which can localise the unusual objects. It further experimentally compares the adapted methods to a new dataset derived from existing semantic segmentation datasets, proposing a new metric for the task. The evaluation shows that the performance ranking of the compared methods successfully transfers to the new task.en
dc.publisherUniversity of Waterlooen
dc.subjectSemantic Segmentationen
dc.subjectOut of Distribution Detectionen
dc.subjectDeep Learningen
dc.subjectConvolutional Neural Networksen
dc.titleTowards Pixel-Level OOD Detection for Semantic Segmentationen
dc.typeMaster Thesisen
dc.pendingfalse R. Cheriton School of Computer Scienceen Scienceen of Waterlooen
uws-etd.degreeMaster of Mathematicsen
uws.contributor.advisorCzarnecki, Krzysztof
uws.contributor.affiliation1Faculty of Mathematicsen

Files in this item


This item appears in the following Collection(s)

Show simple item record


University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages