Weakly supervised deep convolutional networks for fine-grained object recognition in multispectral images

Simple item page
buir.contributor.authorAygüneş, Bulut
buir.contributor.authorAksoy, Selim
dc.citation.epage1481en_US
dc.citation.spage1478en_US
dc.contributor.authorAygüneş, Buluten_US
dc.contributor.authorAksoy, Selimen_US
dc.contributor.authorCinbiş, R. G.en_US
dc.coverage.spatialYokohama, Japanen_US
dc.date.accessioned2020-01-29T06:37:21Z
dc.date.available2020-01-29T06:37:21Z
dc.date.issued2019
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 28 July-2 August 2019en_US
dc.descriptionConference Name: 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019en_US
dc.description.abstractThe challenging task of training object detectors for fine-grained classification faces additional difficulties when there are registration errors between the image data and the ground truth. We propose a weakly supervised learning methodology for the classification of 40 types of trees by using fixed-sized multispectral images with a class label but with no exact knowledge of the object location. Our approach consists of an end-to-end trainable convolutional neural network with separate branches for learning class-specific and location-specific scoring of image regions. Comparative experiments show that the proposed method simultaneously learns to detect and classify the objects of interest with high accuracy.en_US
dc.description.provenanceSubmitted by Zeynep Aykut (zeynepay@bilkent.edu.tr) on 2020-01-29T06:37:21Z No. of bitstreams: 1 Weakly_supervised_deep_convolutional_networks_for_fine-grained_object_recognition_in_multispectral_'mages.pdf: 294645 bytes, checksum: 1c79b8268e041be908688b2b22a8c901 (MD5)en
dc.description.provenanceMade available in DSpace on 2020-01-29T06:37:21Z (GMT). No. of bitstreams: 1 Weakly_supervised_deep_convolutional_networks_for_fine-grained_object_recognition_in_multispectral_'mages.pdf: 294645 bytes, checksum: 1c79b8268e041be908688b2b22a8c901 (MD5) Previous issue date: 2019en
dc.description.sponsorshipInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.description.sponsorshipGeoscience and Remote Sensing Society (GRSS)en_US
dc.identifier.doi10.1109/IGARSS.2019.8899170en_US
dc.identifier.eisbn9781538691540
dc.identifier.eissn2153-7003
dc.identifier.isbn9781538691557
dc.identifier.issn2153-6996
dc.identifier.urihttp://hdl.handle.net/11693/52890
dc.language.isoEnglishen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.isversionofhttps://dx.doi.org/10.1109/IGARSS.2019.8899170en_US
dc.source.titleInternational Geoscience and Remote Sensing Symposium, IGARSS 2019en_US
dc.subjectWeakly supervised learningen_US
dc.subjectObject recognitionen_US
dc.subjectMultispectral image analysisen_US
dc.titleWeakly supervised deep convolutional networks for fine-grained object recognition in multispectral imagesen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Weakly_supervised_deep_convolutional_networks_for_fine-grained_object_recognition_in_multispectral_'mages.pdf
Size:
287.74 KB
Format:
Adobe Portable Document Format
Description:
View / Download
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Publications - Computer Engineering