Home > Research > Publications & Outputs > A2-FPN for semantic segmentation of fine-resolu...

Electronic data

  • TRES-PAP-2021

    Submitted manuscript, 37.1 MB, PDF document

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License


Text available via DOI:

View graph of relations

A2-FPN for semantic segmentation of fine-resolution remotely sensed images

Research output: Contribution to Journal/MagazineJournal articlepeer-review

  • Rui Li
  • Libo Wang
  • Ce Zhang
  • Chenxi Duan
  • Shunyi Zheng
<mark>Journal publication date</mark>28/02/2022
<mark>Journal</mark>International Journal of Remote Sensing
Issue number3
Number of pages26
Pages (from-to)1131-1155
Publication StatusPublished
Early online date26/02/22
<mark>Original language</mark>English


The thriving development of earth observation technology makes more and more high-resolution remote-sensing images easy to obtain. However, caused by fine-resolution, the huge spatial and spectral complexity leads to the automation of semantic segmentation becoming a challenging task. Addressing such an issue represents an exciting research field, which paves the way for scene-level landscape pattern analysis and decision-making. To tackle this problem, we propose an approach for automatic land segmentation based on the Feature Pyramid Network (FPN). As a classic architecture, FPN can build a feature pyramid with high-level semantics throughout. However, intrinsic defects in feature extraction and fusion hinder FPN from further aggregating more discriminative features. Hence, we propose an Attention Aggregation Module (AAM) to enhance multiscale feature learning through attention-guided feature aggregation. Based on FPN and AAM, a novel framework named Attention Aggregation Feature Pyramid Network (A2-FPN) is developed for semantic segmentation of fine-resolution remotely sensed images. Extensive experiments conducted on four datasets demonstrate the effectiveness of our A2-FPN in segmentation accuracy. Code is available at https://github.com/lironui/A2-FPN.