Показати скорочений опис матеріалу
dc.contributor.author | Viniavskyi, Ostap![]() |
|
dc.date.accessioned | 2021-09-09T09:23:48Z | |
dc.date.available | 2021-09-09T09:23:48Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | Viniavskyi, Ostap. Learning Discriminative Context-Aware Keypoints Representations for Resolving Ambiguous Matches: Bachelor Thesis: manuscript / Ostap Viniavskyi; Supervisor: PhD James Pritts; Ukrainian Catholic University, Department of Computer Sciences. – Lviv: 2021. – 40 p.: ill. | uk |
dc.identifier.uri | https://er.ucu.edu.ua/handle/1/2874 | |
dc.description.abstract | In the feature matching problem, local keypoint representations are often not sufficiently distinctive to disambiguate repetitive textures. State-of-the-art matching pipelines encode global information and embed context into keypoint descriptors to resolve this issue. In this thesis, we evaluate the failure modes of the state-ofthe- art method for image matching. We identify the problem that including global context to keypoint representations can sometimes eliminate their distinctiveness. We propose to enhance the learning of the state-of-the-art pipeline by adding a metric learning component to its objective function. By learning more distinctive global context-aware keypoint descriptors, we recover the filtered matches without the loss in matching precision. | uk |
dc.language.iso | en | uk |
dc.title | Learning Discriminative Context-Aware Keypoints Representations for Resolving Ambiguous Matches | uk |
dc.type | Preprint | uk |
dc.status | Публікується вперше | uk |