Detecting and Grouping Identical Objects for Region Proposal and ClassificationVise andre og tillknytning
2017 (engelsk)Inngår i: 2017 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, 2017, Vol. 2017, s. 501-502, artikkel-id 8014810Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]
Often multiple instances of an object occur in the same scene, for example in a warehouse. Unsupervised multi-instance object discovery algorithms are able to detect and identify such objects. We use such an algorithm to provide object proposals to a convolutional neural network (CNN) based classifier. This results in fewer regions to evaluate, compared to traditional region proposal algorithms. Additionally, it enables using the joint probability of multiple instances of an object, resulting in improved classification accuracy. The proposed technique can also split a single class into multiple sub-classes corresponding to the different object types, enabling hierarchical classification.
sted, utgiver, år, opplag, sider
IEEE Computer Society, 2017. Vol. 2017, s. 501-502, artikkel-id 8014810
Serie
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, ISSN 2160-7508
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-218547DOI: 10.1109/CVPRW.2017.76ISI: 000426448300070Scopus ID: 2-s2.0-85030248255ISBN: 9781538607336 (tryckt)OAI: oai:DiVA.org:kth-218547DiVA, id: diva2:1161444
Konferanse
30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, Honolulu, United States, 21 July 2017 through 26 July 2017
Merknad
QC 20171130
2017-11-302017-11-302018-03-22bibliografisk kontrollert