EMBANet: A flexible efficient multi-branch attention network.

Journal: Neural networks : the official journal of the International Neural Network Society
PMID:

Abstract

Recent advances in the design of convolutional neural networks have shown that performance can be enhanced by improving the ability to represent multi-scale features. However, most existing methods either focus on designing more sophisticated attention modules, which leads to higher computational costs, or fail to effectively establish long-range channel dependencies, or neglect the extraction and utilization of structural information. This work introduces a novel module, the Multi-Branch Concatenation (MBC), designed to process input tensors and extract multi-scale feature maps. The MBC module introduces new degrees of freedom (DoF) in the design of attention networks by allowing for flexible adjustments to the types of transformation operators and the number of branches. This study considers two key transformation operators: multiplexing and splitting, both of which facilitate a more granular representation of multi-scale features and enhance the receptive field range. By integrating the MBC with an attention module, a Multi-Branch Attention (MBA) module is developed to capture channel-wise interactions within feature maps, thereby establishing long-range channel dependencies. Replacing the 3x3 convolutions in the bottleneck blocks of ResNet with the proposed MBA yields a new block, the Efficient Multi-Branch Attention (EMBA), which can be seamlessly integrated into state-of-the-art backbone CNN models. Furthermore, a new backbone network, named EMBANet, is constructed by stacking EMBA blocks. The proposed EMBANet has been thoroughly evaluated across various computer vision tasks, including classification, detection, and segmentation, consistently demonstrating superior performance compared to popular backbones.

Authors

  • Keke Zu
    Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, Zhejiang, China; Shenzhen Key Laboratory of Advanced Machine Learning and Applications, Shenzhen University, Shenzhen, China. Electronic address: zukeke@csj.uestc.edu.cn.
  • Hu Zhang
    Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu, China.
  • Lei Zhang
    Division of Gastroenterology, Union Hospital, Tongji Medical College Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Jian Lu
    Key Laboratory of Microelectronic Devices & Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, China.
  • Chen Xu
    Department of Mathematics and Statistics, University of Ottawa, Ottawa, ON K1N 6N5, Canada.
  • Hongyang Chen
    Zhejiang Lab, Hangzhou, China.
  • Yu Zheng
    Department of Thoracic Surgery, West China Hospital of Sichuan University, Chengdu 610041, China.