DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Vision Transformers-Reference-Cited by-同舟云学术

DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Vision Transformers

Author:

Li Changlin¹^ORCID,Wang Guangrun²,Wang Bing³,Liang Xiaodan⁴^ORCID,Li Zhihui⁵^ORCID,Chang Xiaojun¹

Affiliation:

1. Australian Artificial Intelligence Institute, University of Technology Sydney, Australia

2. Oxford University, U.K.

3. Alibaba Group, China

4. Sun Yat-sen University, China

5. Shandong Artificial Intelligence, Qilu University of Technology (Shandong Academy of Sciences), China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

Reference123 articles.

1. Dynamic capacity networks;almahairi;Proc Int Conf Mach Learn,2016

2. AlphaNet: Improved training of supernet with alpha-divergence;wang;Proc Int Conf Mach Learn,2021

4. Conditional computation in neural networks for faster models;bengio;Workshop Track Proc Int Conf Learn Representations,2016

Cited by 33 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

5. Multi-scale frequency domain learning for texture classification;International Journal of Machine Learning and Cybernetics;2024-08-14