Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Changyong Shu"'
Publikováno v:
Journal of Aerospace Technology and Management, Vol 8, Iss 2, Pp 152-162 (2016)
The accurate micro-motions recognition of spatial cone target is the foundation of the characteristic parameter acquisition. For this reason, a micro-motion recognition method based on the distinguishing characteristics extracted from the Inverse Syn
Externí odkaz:
https://doaj.org/article/1443bb48da354613899d9e08859329db
Publikováno v:
Journal of Aerospace Technology and Management, Vol 7, Iss 3 (2015)
The original radar cross section data or some rough models are often used to estimate a given aircraft target detection probability. The calculation results may not be very accurate as targets are different from one another and the real radar detecti
Externí odkaz:
https://doaj.org/article/26cc19784be8464ab91e4d7f5a9369c0
Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial training to
Externí odkaz:
http://arxiv.org/abs/1904.05100
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:7035-7049
In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly borrow the d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2d7fd83ae6c8f16646101dd7a076bbf0
https://doi.org/10.1109/tpami.2020.3001940
https://doi.org/10.1109/tpami.2020.3001940
Knowledge distillation (KD) has been proven to be a simple and effective tool for training compact models. Almost all KD variants for dense prediction tasks align the student and teacher networks' feature maps in the spatial domain, typically by mini
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c17e3e6a4af7e5f055c06e5af30f7812
Publikováno v:
Journal of Aerospace Technology and Management, Vol 8, Iss 2, Pp 152-162 (2016)
Journal of Aerospace Technology and Management v.8 n.2 2016
Journal of Aerospace Technology and Management
Departamento de Ciência e Tecnologia Aeroespacial (DCTA)
instacron:DCTA
Journal of Aerospace Technology and Management, Volume: 8, Issue: 2, Pages: 152-162, Published: JUN 2016
Journal of Aerospace Technology and Management v.8 n.2 2016
Journal of Aerospace Technology and Management
Departamento de Ciência e Tecnologia Aeroespacial (DCTA)
instacron:DCTA
Journal of Aerospace Technology and Management, Volume: 8, Issue: 2, Pages: 152-162, Published: JUN 2016
The accurate micro-motions recognition of spatial cone target is the foundation of the characteristic parameter acquisition. For this reason, a micro-motion recognition method based on the distinguishing characteristics extracted from the Inverse Syn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2ee45d66e055102c4b5d06b8c5d1eb7f
https://doi.org/10.5028/jatm.v8i2.603
https://doi.org/10.5028/jatm.v8i2.603
Publikováno v:
Journal of Aerospace Technology and Management. 7:314-322
The original radar cross section data or some rough models are often used to estimate a given aircraft target detection probability. The calculation results may not be very accurate as targets are different from one another and the real radar detecti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bed27bea52021bfab505b0c7725f5058
https://doi.org/10.5028/jatm.v7i3.470
https://doi.org/10.5028/jatm.v7i3.470