Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Linhang Cai"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:140-148
We proposed a Prior Gradient Mask Guided Pruning-aware Fine-Tuning (PGMPF) framework to accelerate deep Convolutional Neural Networks (CNNs). In detail, the proposed PGMPF selectively suppresses the gradient of those ”unimportant” parameters via
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3f20133a5b8f199250be62ea358aadd
https://doi.org/10.1609/aaai.v36i1.19888
https://doi.org/10.1609/aaai.v36i1.19888
Autor:
Chuanguang Yang, Zhulin An, Helong Zhou, Linhang Cai, Xiang Zhi, Jiwen Wu, Yongjun Xu, Qian Zhang
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200526
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::044f717100d828c9da2c750ce86dc85e
https://doi.org/10.1007/978-3-031-20053-3_31
https://doi.org/10.1007/978-3-031-20053-3_31
Knowledge distillation (KD) is an effective framework that aims to transfer meaningful information from a large teacher to a smaller student. Generally, KD often involves how to define and transfer knowledge. Previous KD methods often focus on mining
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b151c31c56c0eaed20954c0b04178002
http://arxiv.org/abs/2109.03075
http://arxiv.org/abs/2109.03075
Publikováno v:
IJCAI
Knowledge distillation often involves how to define and transfer knowledge from teacher to student effectively. Although recent self-supervised contrastive knowledge achieves the best performance, forcing the network to learn such knowledge may damag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::84e77f412b083c2e54f2ce3932cc1708
https://doi.org/10.24963/ijcai.2021/168
https://doi.org/10.24963/ijcai.2021/168
Publikováno v:
IJCNN
Filter pruning is widely used to reduce the computation of deep learning, enabling the deployment of Deep Neural Networks (DNNs) in resource-limited devices. Conventional Hard Filter Pruning (HFP) method zeroizes pruned filters and stops updating the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d216f8eebc479ec86b468cf16d558080
https://doi.org/10.1109/ijcnn52387.2021.9534116
https://doi.org/10.1109/ijcnn52387.2021.9534116
We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::deeaea563f5001370f224681ab214bf5
Publikováno v:
ICPR
Network pruning is widely used to compress Deep Neural Networks (DNNs). The Soft Filter Pruning (SFP) method zeroizes the pruned filters during training while updating them in the next training epoch. Thus the trained information of the pruned filter
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2307948531284cc5a9aa0edab631185