A Compact Version of EfficientNet

Please use this identifier to cite or link to this item: https://elib.vku.udn.vn/handle/123456789/2723

Full metadata record

DC Field	Value	Language
dc.contributor.author	Hoang, Van Thanh	-
dc.contributor.author	Tu, Minh Phuong	-
dc.contributor.author	Kang-Hyun, Jo	-
dc.date.accessioned	2023-09-26T01:34:27Z	-
dc.date.available	2023-09-26T01:34:27Z	-
dc.date.issued	2023-07	-
dc.identifier.isbn	978-3-031-36886-8	-
dc.identifier.uri	https://link.springer.com/chapter/10.1007/978-3-031-36886-8_25	-
dc.identifier.uri	http://elib.vku.udn.vn/handle/123456789/2723	-
dc.description	Lecture Notes in Networks and Systems (LNNS, volume 734); CITA: Conference on Information Technology and its Applications; pp: 297-305.	vi_VN
dc.description.abstract	EfficientNet is a convolutional neural network architecture that was created by doing a neural architecture search with the AutoML MNAS framework, which optimized both accuracy and efficiency. It is based on MobileNetV2’s inverted bottleneck residual blocks, as well as squeeze-and-excite blocks. With far lower parameter computation burdens on the ImageNet challenge, EfficientNet may compete with the best. This paper provides a mobile version of EfficientNet that has accuracy similar to the ImageNet dataset but runs nearly twice as fast.	vi_VN
dc.language.iso	en	vi_VN
dc.publisher	Springer Nature	vi_VN
dc.subject	EfficientNet	vi_VN
dc.subject	MobileNetV2	vi_VN
dc.subject	AutoML MNAS framework	vi_VN
dc.title	A Compact Version of EfficientNet	vi_VN
dc.type	Working Paper	vi_VN
Appears in Collections:	CITA 2023 (International)

Files in This Item: