Fine-grained object recognition and zero-shot learning in remote sensing imagery

Simple item page
buir.contributor.authorSümbül, Gencer
buir.contributor.authorSelim Aksoy
dc.citation.epage779en_US
dc.citation.issueNumber2en_US
dc.citation.spage770en_US
dc.citation.volumeNumber56en_US
dc.contributor.authorSümbül, Genceren_US
dc.contributor.authorCinbis, R. G.en_US
dc.contributor.authorSelim Aksoyen_US
dc.date.accessioned2019-02-12T07:56:09Z
dc.date.available2019-02-12T07:56:09Z
dc.date.issued2018en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractFine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised algorithms fail to handle this problem where there is low betweenclass variance and high within-class variance for the classes of interest with small sample sizes. We study an even more extreme scenario named zero-shot learning (ZSL) in which no training example exists for some of the classes. ZSL aims to build a recognition model for new unseen categories by relating them to seen classes that were previously learned. We establish this relation by learning a compatibility function between image features extracted via a convolutional neural network and auxiliary information that describes the semantics of the classes of interest by using training samples from the seen classes. Then, we show how knowledge transfer can be performed for the unseen classes by maximizing this function during inference. We introduce a new data set that contains 40 different types of street trees in 1-ft spatial resolution aerial data, and evaluate the performance of this model with manually annotated attributes, a natural language model, and a scientific taxonomy as auxiliary information. The experiments show that the proposed model achieves 14.3% recognition accuracy for the classes with no training examples, which is significantly better than a random guess accuracy of 6.3% for 16 test classes, and three other ZSL algorithms.en_US
dc.identifier.doi10.1109/TGRS.2017.2754648en_US
dc.identifier.eissn1558-0644
dc.identifier.issn0196-2892
dc.identifier.urihttp://hdl.handle.net/11693/49294
dc.language.isoEnglishen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.relation.isversionofhttp://doi.org/10.1109/TGRS.2017.2754648en_US
dc.source.titleIEEE Transactions on Geoscience and Remote Sensingen_US
dc.subjectFine-grained classificationen_US
dc.subjectObject recognitionen_US
dc.subjectZero-shot learning (ZSL)en_US
dc.titleFine-grained object recognition and zero-shot learning in remote sensing imageryen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Fine-grained_object_recognition_and_zero-shot_learning_in_remote_sensing_imagery.pdf
Size:
3.72 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
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
Department of Computer Engineering