Web: http://arxiv.org/abs/2209.07947

Sept. 19, 2022, 1:11 a.m. | Chao Li, Aojun Zhou, Anbang Yao

cs.LG updates on arXiv.org arxiv.org

Learning a single static convolutional kernel in each convolutional layer is
the common training paradigm of modern Convolutional Neural Networks (CNNs).
Instead, recent research in dynamic convolution shows that learning a linear
combination of $n$ convolutional kernels weighted with their input-dependent
attentions can significantly improve the accuracy of light-weight CNNs, while
maintaining efficient inference. However, we observe that existing works endow
convolutional kernels with the dynamic property through one dimension
(regarding the convolutional kernel number) of the kernel space, but …

arxiv convolution

More from arxiv.org / cs.LG updates on arXiv.org

Postdoctoral Fellow: ML for autonomous materials discovery

@ Lawrence Berkeley National Lab | Berkeley, CA

Research Scientists

@ ODU Research Foundation | Norfolk, Virginia

Embedded Systems Engineer (Robotics)

@ Neo Cybernetica | Bedford, New Hampshire

2023 Luis J. Alvarez and Admiral Grace M. Hopper Postdoc Fellowship in Computing Sciences

@ Lawrence Berkeley National Lab | San Francisco, CA

Senior Manager Data Scientist

@ NAV | Remote, US

Senior AI Research Scientist

@ Earth Species Project | Remote anywhere

Research Fellow- Center for Security and Emerging Technology (Multiple Opportunities)

@ University of California Davis | Washington, DC

Staff Fellow - Data Scientist

@ U.S. FDA/Center for Devices and Radiological Health | Silver Spring, Maryland

Staff Fellow - Senior Data Engineer

@ U.S. FDA/Center for Devices and Radiological Health | Silver Spring, Maryland

Computational Linguist

@ Constant Contact | Waterloo, ON/Hybrid, ON

Senior Data Scientist

@ Advian | Espoo, Finland

Data Scientist, EU In-stock Management

@ Gopuff | London, England