# SGDM: Static-Guided Dynamic Module Make Stronger Visual Models

arXiv: https://arxiv.org/abs/2403.18282 · HTML: https://mlsanity.com/paper/2403.18282/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 27 Mar 2024.

## Builds on (most cited first, 17 of 17)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [YOLOv6 v3.0: A Full-Scale Reloading](https://mlsanity.com/paper/2301.05586/) (2023)
- [Omni-Dimensional Dynamic Convolution](https://mlsanity.com/paper/2209.07947/) (2022)
- [Decoupled Dynamic Filter Networks](https://mlsanity.com/paper/2104.14107/) (2021)
- [WeightNet: Revisiting the Design Space of Weight Networks](https://mlsanity.com/paper/2007.11823/) (2020)
- [DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks](https://mlsanity.com/paper/2004.10694/) (2020)
- [Revisiting Dynamic Convolution via Matrix Decomposition](https://mlsanity.com/paper/2103.08756/) (2021)
- [Gaussian Dynamic Convolution for Efficient Single-Image Segmentation](https://mlsanity.com/paper/2104.08783/) (2021)
- [RFAConv: Receptive-Field Attention Convolution for Improving Convolutional Neural Networks](https://mlsanity.com/paper/2304.03198/) (2023)

## Abstract (arXiv)

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 generate certain features, we vastly reduce the parameters of the entire dynamic convolution operation. Secondly, we added a spatial branch inside RDConv to generate convolutional kernel parameters with richer spatial information. Embedding dynamic convolution will also bring the problem of sensitivity to high-frequency noise. We propose the Static-Guided Dynamic Module (SGDM) to address this limitation. By using SGDM, we utilize a set of asymmetric static convolution kernel parameters to guide the construction of dynamic convolution. We introduce the mechanism of shared weights in static convolution to solve the problem of dynamic convolution being sensitive to high-frequency noise. Extensive experiments illustrate that multiple different object detection backbones equipped with SGDM achieve a highly competitive boost in performance(e.g., +4% mAP with YOLOv5n on VOC and +1.7% mAP with YOLOv8n on COCO) with negligible parameter increase(i.e., +0.33M on YOLOv5n and +0.19M on YOLOv8n).