Full metadata record
DC FieldValueLanguage
dc.contributor.authorHuang, Mou-Yueen_US
dc.contributor.authorLai, Ching-Haoen_US
dc.contributor.authorChen, Sin-Horngen_US
dc.date.accessioned2018-08-21T05:57:14Z-
dc.date.available2018-08-21T05:57:14Z-
dc.date.issued2017-01-01en_US
dc.identifier.issn1522-4880en_US
dc.identifier.urihttp://hdl.handle.net/11536/147215-
dc.description.abstractIn order to achieve higher accuracy of image recognition, deeper and wider networks have been used. However, when the network size gets bigger, its forward inference time also takes longer. To address this problem, we propose Deeply Fused Branchy Network (DFB-Net) by adding small but complete side branches to the target baseline main branch. DFB-Net allows easy-to-discriminate samples to be classified faster. For hard-to-discriminate samples, DFB-Net makes probability fusion by averaging softmax probabilities to make collaborative predictions. Extensive experiments on the two CIFAR datasets show that DFB-Net achieves state-ofthe-art results to obtain an error rate of 3.07% on CIFAR-10 and 16.01% on CIFAR-100. Meanwhile, the forward inference time (with a batch size of 1 and averaged among all test samples) only takes 10.4 ms on CIFAR-10, 18.8 ms on CIFAR-100, using GTX 1080 GPU with cuDNN 5.1.en_US
dc.language.isoen_USen_US
dc.subjectDeep learningen_US
dc.subjectconvolutional neural networken_US
dc.subjectimage recognitionen_US
dc.subjectclassificationen_US
dc.subjectinference timeen_US
dc.titleFAST AND ACCURATE IMAGE RECOGNITION USING DEEPLY-FUSED BRANCHY NETWORKSen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)en_US
dc.citation.spage2876en_US
dc.citation.epage2880en_US
dc.contributor.department電機工程學系zh_TW
dc.contributor.departmentDepartment of Electrical and Computer Engineeringen_US
dc.identifier.wosnumberWOS:000428410703001en_US
Appears in Collections:Conferences Paper