Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Tan, Sia huat"'
Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data examples; (2) t
Externí odkaz:
http://arxiv.org/abs/2305.00918
Publikováno v:
The British Machine Vision Conference (BMVC) 2021
Most feedforward convolutional neural networks spend roughly the same efforts for each pixel. Yet human visual recognition is an interaction between eye movements and spatial attention, which we will have several glimpses of an object in different re
Externí odkaz:
http://arxiv.org/abs/2111.02018
Autor:
Tan, Zhanhong, Song, Jiebo, Ma, Xiaolong, Tan, Sia-Huat, Chen, Hongyang, Miao, Yuanqing, Wu, Yifu, Ye, Shaokai, Wang, Yanzhi, Li, Dehui, Ma, Kaisheng
Weight pruning is a powerful technique to realize model compression. We propose PCNN, a fine-grained regular 1D pruning method. A novel index format called Sparsity Pattern Mask (SPM) is presented to encode the sparsity in PCNN. Leveraging SPM with l
Externí odkaz:
http://arxiv.org/abs/2002.04997
Autor:
Ye, Shaokai, Wu, Kailu, Zhou, Mu, Yang, Yunfei, Tan, Sia huat, Xu, Kaidi, Song, Jiebo, Bao, Chenglong, Ma, Kaisheng
Existing domain adaptation methods aim at learning features that can be generalized among domains. These methods commonly require to update source classifier to adapt to the target domain and do not properly handle the trade off between the source do
Externí odkaz:
http://arxiv.org/abs/1911.12796
Autor:
Ma, Xiaolong, Lin, Sheng, Ye, Shaokai, He, Zhezhi, Zhang, Linfeng, Yuan, Geng, Tan, Sia Huat, Li, Zhengang, Fan, Deliang, Qian, Xuehai, Lin, Xue, Ma, Kaisheng, Wang, Yanzhi
Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compressi
Externí odkaz:
http://arxiv.org/abs/1907.02124
A human does not have to see all elephants to recognize an animal as an elephant. On contrast, current state-of-the-art deep learning approaches heavily depend on the variety of training samples and the capacity of the network. In practice, the size
Externí odkaz:
http://arxiv.org/abs/1905.12171
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Ma, Xiaolong, Lin, Sheng, Ye, Shaokai, He, Zhezhi, Zhang, Linfeng, Yuan, Geng, Tan, Sia Huat, Li, Zhengang, Fan, Deliang, Qian, Xuehai, Lin, Xue, Ma, Kaisheng, Wang, Yanzhi
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems; September 2022, Vol. 33 Issue: 9 p4930-4944, 15p
