GoodPoint: unsupervised learning of keypoint detection and description
This paper introduces a new algorithm for unsupervised learning of keypoint detectors and descriptors, which demonstrates fast convergence and good performance across different datasets. The training procedure uses homographic transformation of images. The proposed model learns to detect points and...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Journal Article |
| Language: | English |
| Published: |
01-06-2020
|
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | This paper introduces a new algorithm for unsupervised learning of keypoint
detectors and descriptors, which demonstrates fast convergence and good
performance across different datasets. The training procedure uses homographic
transformation of images. The proposed model learns to detect points and
generate descriptors on pairs of transformed images, which are easy for it to
distinguish and repeatedly detect. The trained model follows SuperPoint
architecture for ease of comparison, and demonstrates similar performance on
natural images from HPatches dataset, and better performance on retina images
from Fundus Image Registration Dataset, which contain low number of corner-like
features. For HPatches and other datasets, coverage was also computed to
provide better estimation of model quality. |
|---|---|
| AbstractList | This paper introduces a new algorithm for unsupervised learning of keypoint
detectors and descriptors, which demonstrates fast convergence and good
performance across different datasets. The training procedure uses homographic
transformation of images. The proposed model learns to detect points and
generate descriptors on pairs of transformed images, which are easy for it to
distinguish and repeatedly detect. The trained model follows SuperPoint
architecture for ease of comparison, and demonstrates similar performance on
natural images from HPatches dataset, and better performance on retina images
from Fundus Image Registration Dataset, which contain low number of corner-like
features. For HPatches and other datasets, coverage was also computed to
provide better estimation of model quality. |
| Author | Belikov, Anatoly Potapov, Alexey |
| Author_xml | – sequence: 1 givenname: Anatoly surname: Belikov fullname: Belikov, Anatoly – sequence: 2 givenname: Alexey surname: Potapov fullname: Potapov, Alexey |
| BackLink | https://doi.org/10.48550/arXiv.2006.01030$$DView paper in arXiv |
| BookMark | eNotj01OwzAQhb2ABZQeoCt8gYSJE8cJO1TRUqkSLLqPRuMxsih25KQVvT1JYfX09H6k717chBhYiFUBedVoDU-Yfvw5VwB1DgWUcCc22xjtR_RhfJanMJx6Tmc_sJVHxhR8-JTRyS--9HNFWh6ZRh-DxGAnN1Dy_ewfxK3D48DLf12Iw-b1sH7L9u_b3fpln2FtIGNqHLcKscCCTQNGVcbZWrWNIa7JGV1poJaQmIGaKWCnWFuAaUPalQvx-Hd7Ben65L8xXboZqLsClb9ly0lk |
| ContentType | Journal Article |
| Copyright | http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| Copyright_xml | – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| DBID | AKY GOX |
| DOI | 10.48550/arxiv.2006.01030 |
| DatabaseName | arXiv Computer Science arXiv.org |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| ExternalDocumentID | 2006_01030 |
| GroupedDBID | AKY GOX |
| ID | FETCH-LOGICAL-a670-ec8fe92aa1a1e7807247fd62987ce6cf75450c9cacee0c8629ef2e5d002aac5f3 |
| IEDL.DBID | GOX |
| IngestDate | Mon Jan 08 05:50:06 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a670-ec8fe92aa1a1e7807247fd62987ce6cf75450c9cacee0c8629ef2e5d002aac5f3 |
| OpenAccessLink | https://arxiv.org/abs/2006.01030 |
| ParticipantIDs | arxiv_primary_2006_01030 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-06-01 |
| PublicationDateYYYYMMDD | 2020-06-01 |
| PublicationDate_xml | – month: 06 year: 2020 text: 2020-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationYear | 2020 |
| Score | 1.7720584 |
| SecondaryResourceType | preprint |
| Snippet | This paper introduces a new algorithm for unsupervised learning of keypoint
detectors and descriptors, which demonstrates fast convergence and good
performance... |
| SourceID | arxiv |
| SourceType | Open Access Repository |
| SubjectTerms | Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning |
| Title | GoodPoint: unsupervised learning of keypoint detection and description |
| URI | https://arxiv.org/abs/2006.01030 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://sdu.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV07T8MwED7RTiwIBKg85YE1InWb2GFD0JQJkOjQrTrbZ9QlqZoG8fM5O-GxMNq-xWef7z6ffR_AjbOBjDxTyZQ8MkDBLDFZPuG9rA1J51xmInXCm3pe6sdZKJMjvv_C4PZz_dHVBzbNbZcrCExYAxhIGZ5szV-WXXIyluLq5X_lOMaMXX-cRHkIB310J-675TiCPaqOoZzXtXut19XuTrRV026CeTbkRM_Y8C5qL9iWNkFEONrF11GVYIzPrR-zPoFFOVs8PCU9fUGCuUoTstpTIRHHOCalUyWnyrtcMsi3lFuvOHZJbWGR3VRqGVgU5CVljo8oRJv5ySkMq7qiEQg78exqCjSocaqLsQmux5pUK-7gGOIMRnHSq01XoSJwS-arqI_z_4cuYF8G8BivFC5huNu2dAWDxrXXUc1fOqJ85w |
| link.rule.ids | 228,230,782,887 |
| linkProvider | Cornell University |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=GoodPoint%3A+unsupervised+learning+of+keypoint+detection+and+description&rft.au=Belikov%2C+Anatoly&rft.au=Potapov%2C+Alexey&rft.date=2020-06-01&rft_id=info:doi/10.48550%2Farxiv.2006.01030&rft.externalDocID=2006_01030 |