Results 221 to 230 of about 14,609 (251)

Pruning 3D Filters For Accelerating 3D ConvNets

IEEE Transactions on Multimedia, 2020
Many methods have been proposed to accelerate 2D ConvNets by removing redundant parameters. However, few efforts are devoted to the problem of accelerating 3D Convolutional Networks. The 3D ConvNets, which are mainly designed for extracting spatiotemporal features, have been widely used in many video analytics tasks, such as action recognition and ...
Zhenzhen Wang, Weixiang Hong 0001, Yap-Peng Tan, Junsong Yuan 0001   +3 more
openaire   +1 more source

DDFP:A data driven filter pruning method with pruning compensation

Journal of Visual Communication and Image Representation, 2023
Guoqiang Li 0002, Bowen Liu, Anbang Chen
openaire   +1 more source

Online Filter Weakening and Pruning for Efficient Convnets

2018 IEEE International Conference on Multimedia and Expo (ICME), 2018
Pruning is an effective method to address the limitation of deploying deep neural networks (DNNs) on embedded systems. Most existing methods prune weights on a given pre-trained DNN followed by a costly fine-tuning process. In this paper, we propose a new and efficient pruning algorithm which can prune the structures of filters and filter shapes ...
Zhengguang Zhou, Wengang Zhou 0001, Richang Hong, Houqiang Li   +3 more
openaire   +1 more source

Filter pruning via expectation-maximization

Neural Computing and Applications, 2022
Sheng Xu 0007, Yanjing Li, Linlin Yang, Baochang Zhang 0001, Dianmin Sun, Kexin Liu   +5 more
openaire   +1 more source

Pruning and aging for user histories in collaborative filtering

2016 IEEE Symposium Series on Computational Intelligence (SSCI), 2016
In this paper, we introduce algorithms for pruning and aging user ratings in collaborative filtering systems, based on their oldness, under the rationale that aged user ratings may not accurately reflect the current state of users regarding their preferences.
Dionisis Margaris, Costas Vassilakis 0001   +1 more
openaire   +1 more source

Filter Pruning Via Softmax Attention

2021 IEEE International Conference on Image Processing (ICIP), 2021
Sungmin Cho, Hyeseong Kim, Junseok Kwon
openaire   +1 more source

Filter Pruning by High-Order Spectral Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Large amount of redundancy is widely present in convolutional neural networks (CNNs). Identifying the redundancy in the network and removing the redundant filters is an effective way to compress the CNN model size with a minimal reduction in performance.
Hang Lin, Yifan Peng, Yubo Zhang 0006, Lin Bie, Xibin Zhao, Yue Gao 0002   +5 more
openaire   +2 more sources

Balanced Stripe-Wise Pruning In The Filter

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
Zheng Huo, Chong Wang 0001, Weiwei Chen, Yuqi Li, Jun Wang 0071, Jiafei Wu   +5 more
openaire   +1 more source

Distortion diminishing with vulnerability filters pruning

Machine Vision and Applications, 2023
Hengyi Huang, Pingfan Wu, Shifeng Xia, Ningzhong Liu   +3 more
openaire   +1 more source

Discrete cosine transform for filter pruning

Applied Intelligence, 2022
Yaosen Chen, Renshuang Zhou, Bing Guo 0004, Yan Shen 0001, Wei Wang 0283, Xuming Wen, Xinhua Suo   +6 more
openaire   +1 more source