Abstract
As the basic and essential component of most object detectors, feature pyramid network (FPN) can effectively extract multi-scale features to recognize objects at different scales. Nevertheless, due to the cross-scale fusion and upsampling operations in FPN, current detectors still suffer from information loss and feature misalignment. To alleviate these problems, a Flow Guided Upsampling Module (FGUM) and a Multi-Feature Attention Module (MFAM) are proposed to improve the FPN. Specifically, FGUM uses a novel flow warp in the upsampling operation to align features, resulting in better cross-scale fusion. At the same time, the MFAM module fully considers the integrity of multi-scale features, and reduces the aliasing effect by optimizing the weight of each level of features. To verify the effectiveness of the improved FPN, it is applied to three state-of-the-art models for experiments, and all of them achieve better detection accuracy compared to the original FPN.
Funding Information
  • Key Laboratory of Land Satellite Remote Sensing Application, Ministry of Natural Resources of China (KLSMNR-K202206)
  • National Natural Science Foundation of China (41801327)
  • National Natural Science Foundation of China (41071424)
  • Priority Academic Program Development of Jiangsu Higher Education Institutions

This publication has 25 references indexed in Scilit: