Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach

Simple item page
dc.contributor.authorTruong, G.
dc.contributor.authorLe, H.
dc.contributor.authorSuter, D.
dc.contributor.authorZhang, E.
dc.contributor.authorGilani, S.Z.
dc.contributor.conferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (19 Jun 2021 - 25 Jun 2021 : virtual online)
dc.date.issued2021
dc.description.abstractRobust model fitting is a core algorithm in a large number of computer vision applications. Solving this problem efficiently for datasets highly contaminated with outliers is, however, still challenging due to the underlying computational complexity. Recent literature has focused on learning-based algorithms. However, most approaches are supervised (which require a large amount of labelled training data). In this paper, we introduce a novel unsupervised learning framework that learns to directly solve robust model fitting. Unlike other methods, our work is agnostic to the underlying input features, and can be easily generalized to a wide variety of LP-type problems with quasiconvex residuals. We empirically show that our method outperforms existing unsupervised learning approaches, and achieves competitive results compared to traditional methods on several important computer vision problems¹.
dc.description.statementofresponsibilityGiang Truong, Huu Le, David Suter, Erchuan Zhang, Syed Zulqarnain Gilani
dc.identifier.citationProceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2021, pp.10343-10352
dc.identifier.doi10.1109/CVPR46437.2021.01021
dc.identifier.isbn9781665445092
dc.identifier.issn1063-6919
dc.identifier.issn2575-7075
dc.identifier.orcidSuter, D. [0000-0001-6306-3023]
dc.identifier.urihttps://hdl.handle.net/2440/139823
dc.language.isoen
dc.publisherIEEE
dc.relation.granthttp://purl.org/au-research/grants/arc/DP200103448
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition
dc.rights©2021 IEEE
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/9577055/proceeding
dc.titleUnsupervised Learning for Robust Fitting: A Reinforcement Learning Approach
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications