CE-FPN: enhancing channel information for object detection

• Published in: Multimedia tools and applications Vol. 81; no. 21; pp. 30685 - 30704
• Main Authors: Luo, Yihao, Cao, Xiang, Zhang, Juntao, Guo, Jingjuan, Shen, Haibo, Wang, Tianjiang, Feng, Qi
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2022; Springer Nature B.V
• Subjects: Aliasing; Computer Communication Networks; Computer Science; Context; Convolution; Data Structures and Information Theory; Deep learning; Feature extraction; Feature maps; Flaw detection; Localization; Multimedia; Multimedia Information Systems; Object recognition; Performance evaluation; Pixels; Reduction; Sensors; Special Purpose and Application-Based Systems; Sub-pixel convolution; Feature pyramid network; Channel enhancement; Object detection

Feature pyramid network (FPN) has been an efficient framework to extract multi-scale features in object detection. However, current FPN-based methods mostly suffer from the intrinsic flaw of channel reduction, which brings about the loss of semantical information. And the miscellaneous feature maps...