Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Xiangxiang Chu"'
Autor:
Chengjian Feng, Yujie Zhong, Zequn Jie, Xiangxiang Chu, Haibing Ren, Xiaolin Wei, Weidi Xie, Lin Ma
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200762
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::941ff80074bd8a883db445152a509ecb
https://doi.org/10.1007/978-3-031-20077-9_41
https://doi.org/10.1007/978-3-031-20077-9_41
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).
To discover powerful yet compact models is an important goal of neural architecture search. Previous two-stage one-shot approaches are limited by search space with a fixed depth. It seems handy to include an additional skip connection in the search s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::540b6f2d5d5a46400ba67e2f43b2c3a4
https://doi.org/10.1109/iccvw54120.2021.00040
https://doi.org/10.1109/iccvw54120.2021.00040
Publikováno v:
ICASSP
Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption. It is however challenging to design models that have both high accuracy and low latency for accurate and fast responsiveness. Many efforts
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a4ba19cfd9223b575bb3f667708904a
https://doi.org/10.1109/icassp39728.2021.9414848
https://doi.org/10.1109/icassp39728.2021.9414848
Publikováno v:
ICPR
Deep convolutional neural networks demonstrate impressive results in the super-resolution domain. A series of studies concentrate on improving peak signal noise ratio (PSNR) by using much deeper layers, which are not friendly to constrained resources
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6454dc43cac55264fe866625a566a37e
https://doi.org/10.1109/icpr48806.2021.9413080
https://doi.org/10.1109/icpr48806.2021.9413080
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695316
ACCV (2)
ACCV (2)
In recent years, deep learning methods have achieved impressive results with higher peak signal-to-noise ratio in Single Image Super-Resolution (SISR) tasks. However, these methods are usually computationally expensive, which constrains their applica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::60714fae3801676a23041013269fb417
https://doi.org/10.1007/978-3-030-69532-3_2
https://doi.org/10.1007/978-3-030-69532-3_2
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585549
ECCV (15)
ECCV (15)
Differentiable Architecture Search (DARTS) is now a widely disseminated weight-sharing neural architecture search method. However, it suffers from well-known performance collapse due to an inevitable aggregation of skip connections. In this paper, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::995a6cc5f12d53712fe435cf4baa81b4
https://doi.org/10.1007/978-3-030-58555-6_28
https://doi.org/10.1007/978-3-030-58555-6_28
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030668228
ECCV Workshops (4)
ECCV Workshops (4)
Fabricating neural models for a wide range of mobile devices is a challenging task due to highly constrained resources. Recent trends favor neural architecture search involving evolutionary algorithms (EA) and reinforcement learning (RL), however, th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::53597ba13943d85d84108bb46cafbbc6
https://doi.org/10.1007/978-3-030-66823-5_6
https://doi.org/10.1007/978-3-030-66823-5_6
Publikováno v:
INTERSPEECH
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden. In this work, we propose a lightweight yet high-performing baseline network inspired by MobileNetV2,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9f1ba891005734aa8394f150de47fc5
http://arxiv.org/abs/1912.12825
http://arxiv.org/abs/1912.12825
Publikováno v:
ICASSP
The evolution of MobileNets has laid a solid foundation for neural network applications on mobile end. With the latest MobileNetV3, neural architecture search again claimed its supremacy in network design. Unfortunately, till today all mobile methods
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2962a18c2d8c72504471d2d9415f587
Autor:
Xiangxiang Chu, Xinjie Yu
Publikováno v:
2012 16th International Symposium on Electromagnetic Launch Technology.
Inductive pulse power supplies are of interest because their energy densities are one order of magnitude higher than those of capacitive power supplies, based on the same power-output capacity. The Institute of Advanced Technology puts forward an ind
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e07c11d2e24f3626de2ea0c75c80ca8d
https://doi.org/10.1109/eml.2012.6325002
https://doi.org/10.1109/eml.2012.6325002