Selective feature connection mechanism: Concatenating multi-layer CNN features with a feature selector
arXiv: Computer Vision and Pattern Recognition(2020)
摘要
•We propose a novel method termed SFCM to fuse CNNs features of different layers.•Our SFCM can be implemented by direct connection and residual connection.•Our SFCM can be used in many existing frameworks to achieve better performance.•We evaluate the SFCM on many different challenging computer vision tasks.
更多查看译文
关键词
Feature combination,Network architecture,Selective feature connection mechanism,Convolutional neural network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要