DECA: a novel multi-scale efficient channel attention module for object detection in real-life fire images

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 52; no. 2; pp. 1362 - 1375
• Main Authors: Wang, Junjie, Yu, Jiong, He, Zhu
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2022; Springer Nature B.V
• Subjects: Artificial Intelligence; Artificial neural networks; Computer Science; Datasets; Deep learning; Efficiency; Experiments; Image detection; Machines; Manufacturing; Mechanical Engineering; Methods; Modules; Neural networks; Object recognition; Parameters; Processes; Sensors; Signal encoding; Attention mechanism; Neural network; Fire detection; Object detection

Channel attention mechanisms have attracted more and more researchers because of their generality and effectiveness in deep convolutional neural networks(DCNNs). However, the signal encoding methods of the current popular channel attention mechanisms are limited. For example, SENet uses the full-con...