Coordinate Attention for Efficient Mobile Network Design

By Qibin Hou, Daquan Zhou, Jiashi Feng. 2021

5,022 citations recorded by the source corpus.

Recent studies on mobile network design have demonstrated the remarkable effectiveness of channel attention (e.g., the Squeeze-and-Excitation attention) for lifting model performance, but they generally neglect the positional information, which is important for generating spatially selective attention maps. In this paper, we propose a novel attention mechanism for mobile networks by embedding positional information into channel attention, which we call "coordinate attention". Unlike channel attention that transforms a feature tensor to a single feature vector via 2D global pooling, the coordinate attention factorizes channel attention into two 1D feature encoding processes that aggregate features along the two spatial directions, respectively. In this way, long-range dependencies can be captured along one spatial direction and meanwhile precise positional information can be preserved along the other spatial direction. The resulting feature maps are then encoded separately into a pair of direction-aware and position-sensitive attention maps that can be complementarily applied to the input feature map to augment the representations of the objects of interest. Our coordinate attention is simple and can be flexibly plugged into classic mobile networks, such as MobileNetV2, MobileNeXt, and EfficientNet with nearly no computational overhead. Extensive experiments demonstrate that our coordinate attention is not only beneficial to ImageNet classification but more interestingly, behaves better in down-stream tasks, such as object detection and semantic segmentation. Code is available at https://github.com/Andrew-Qibin/CoordAttention.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Model Architectures, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jiashi Feng
  2. Qibin Hou
  3. Shuicheng Yan
  4. Zihang Jiang
  5. Li Yuan
  6. Ming-Ming Cheng
  7. Peng-Tao Jiang
  8. Yunhe Wang

In Computer Vision and Pattern Recognition

  1. Jiashi Feng
  2. Shuicheng Yan
  3. Dacheng Tao
  4. Ming-Ming Cheng
  5. Luc Van Gool
  6. Qibin Hou
  7. Ming-Hsuan Yang
  8. Yi Yang

In Electrical and Electronic Engineering

  1. Jiashi Feng
  2. Shuicheng Yan
  3. Liang Wang
  4. Chang Xu
  5. Bingyi Kang
  6. Meng-Hao Guo
  7. Yunhe Wang
  8. Zheng-Ning Liu

In Model Architectures

  1. Jiashi Feng
  2. Qibin Hou
  3. Shuicheng Yan
  4. Li Yuan
  5. Zihang Jiang
  6. Yunhe Wang
  7. Kai Han
  8. Daquan Zhou

In Efficiency & Compression

  1. Li Yuan
  2. Qibin Hou
  3. Shuicheng Yan
  4. Yehui Tang
  5. Liang Wang
  6. Caifeng Shan
  7. Zihang Jiang
  8. Chang Xu

Citations in the corpus