SGDM: Static-Guided Dynamic Module Make Stronger Visual Models

arXiv:2403.18282v1 Announce Type: new
Abstract: The spatial attention mechanism has been widely used to improve object detection performance. However, its operation is currently limited to static convolutions lacking content-adaptive features. This paper innovatively approaches from the perspective of dynamic convolution. We propose Razor Dynamic Convolution (RDConv) to address thetwo flaws in dynamic weight convolution, making it hard to implement in spatial mechanism: 1) it is computation-heavy; 2) when generating weights, spatial information is disregarded. Firstly, by using Razor Operation to …

abstract arxiv attention convolution cs.cv detection dynamic features flaws however object paper performance perspective razor spatial type visual