Abstract

Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited representation capability. To address this issue, we present Dynamic Convolution, a new design that increases model complexity without increasing the network depth or width. Instead of using a single convolution kernel per layer, dynamic convolution aggregates multiple parallel convolution kernels dynamically based upon their attentions, which are input dependent. Assembling multiple kernels is not only computationally efficient due to the small kernel size, but also has more representation power since these kernels are aggregated in a non-linear way via attention. By simply using dynamic convolution for the state-of-the-art architecture MobileNetV3-Small, the top-1 accuracy of ImageNet classification is boosted by 2.9% with only 4% additional FLOPs and 2.9 AP gain is achieved on COCO keypoint detection.

Keywords

Convolution (computer science)FLOPSKernel (algebra)Computer scienceConvolutional neural networkRepresentation (politics)AlgorithmComputational complexity theoryArtificial intelligencePattern recognition (psychology)MathematicsArtificial neural networkParallel computingDiscrete mathematics

Affiliated Institutions

Related Publications

Selective Kernel Networks

In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscie...

2019 2019 IEEE/CVF Conference on Computer ... 2769 citations

Publication Info

Year
2020
Type
article
Pages
11027-11036
Citations
1166
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1166
OpenAlex

Cite This

Yinpeng Chen, Xiyang Dai, Mengchen Liu et al. (2020). Dynamic Convolution: Attention Over Convolution Kernels. , 11027-11036. https://doi.org/10.1109/cvpr42600.2020.01104

Identifiers

DOI
10.1109/cvpr42600.2020.01104