Strengthening Dynamic Convolution With Attention and Residual Connection in Kernel Space

Strengthening Dynamic Convolution With Attention and Residual Connection in Kernel Space

In this paper, we propose Dynamic Residual Convolution (DRConv), an efficient method for computing input-specific local features while addressing the limitations of dynamic convolution. DRConv utilizes global salient features calculated using efficient token attention, strengthening representation p...

Full description

Bibliographic Details
Main Authors: Seokju Yun, Youngmin Ro
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Efficient network
dynamic convolution
transformer
visual backbone
Online Access:https://ieeexplore.ieee.org/document/10409154/

Internet

https://ieeexplore.ieee.org/document/10409154/

Similar Items