Timezone: »

GhostNetV2: Enhance Cheap Operation with Long-Range Attention
Yehui Tang · Kai Han · Jianyuan Guo · Chang Xu · Chao Xu · Yunhe Wang

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #701

Light-weight convolutional neural networks (CNNs) are specially designed for applications on mobile devices with faster inference speed. The convolutional operation can only capture local information in a window region, which prevents performance from being further improved. Introducing self-attention into convolution can capture global information well, but it will largely encumber the actual speed. In this paper, we propose a hardware-friendly attention mechanism (dubbed DFC attention) and then present a new GhostNetV2 architecture for mobile applications. The proposed DFC attention is constructed based on fully-connected layers, which can not only execute fast on common hardware but also capture the dependence between long-range pixels. We further revisit the expressiveness bottleneck in previous GhostNet and propose to enhance expanded features produced by cheap operations with DFC attention, so that a GhostNetV2 block can aggregate local and long-range information simultaneously. Extensive experiments demonstrate the superiority of GhostNetV2 over existing architectures. For example, it achieves 75.3% top-1 accuracy on ImageNet with 167M FLOPs, significantly suppressing GhostNetV1 (74.5%) with a similar computational cost. The source code will be available at https://github.com/huawei-noah/Efficient-AI-Backbones/tree/master/ghostnetv2_pytorch and https://gitee.com/mindspore/models/tree/master/research/cv/ghostnetv2.

Author Information

Yehui Tang (Peking University)
Kai Han (Huawei Noah's Ark Lab)
Jianyuan Guo (University of Sydney)
Chang Xu (University of Sydney)
Chao Xu (Peking University)
Yunhe Wang (Huawei Noah's Ark Lab)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors