DANet: Dual Attention Network for Scene Segmentatio

Last Updated on 10th March 2021 by Li-Wen Wang

Abstract

The paper introduces a position attention module and a channel attention module to capture global dependencies in the spatial and channel dimensions respectively.

The proposed DANet adaptively integrates local semantic features using the self-attention mechanism.

摘要

本文引入了位置关注模块和通道关注模块,分别在空间和通道维度上捕捉全局依赖性。

所提出的DANet利用自注意力机制自适应地集成局部语义特征。

Outline

  • Brief Review: attention mechanism, SE net
  • DANet: Dual Attention Network
  • Experiments: visualization and comparison
  • Conclusion

大纲

  • 回顾:注意机制、SENet
  • DANet: 双重关注网络
  • 实验:可视化和对比
  • 结论

Download: https://connectpolyu-my.sharepoint.com/:p:/g/personal/18048204r_connect_polyu_hk/EbgphNjvYP5Psw5gdgDjInQBs761z4x8FYboKXF2arT6kw?e=haTOHI

Leave a Reply