Dual attention feature fusion and adaptive context for accurate segmentation of very high-resolution remote sensing images

Hao Shi, Jiahe Fan, Yupei Wang*, Liang Chen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

Abstract

Land cover classification of high-resolution remote sensing images aims to obtain pixel-level land cover understanding, which is often modeled as semantic segmentation of remote sensing images. In recent years, convolutional network (CNN)-based land cover classification methods have achieved great advancement. However, previous methods fail to generate fine segmentation results, especially for the object boundary pixels. In order to obtain boundary-preserving predictions, we first propose to incorporate spatially adapting contextual cues. In this way, objects with similar appearance can be effectively distinguished with the extracted global contextual cues, which are very helpful to identify pixels near object boundaries. On this basis, low-level spatial details and high-level semantic cues are effectively fused with the help of our proposed dual attention mechanism. Concretely, when fusing multi-level features, we utilize the dual attention feature fusion module based on both spatial and channel attention mechanisms to relieve the influence of the large gap, and further improve the segmentation accuracy of pixels near object boundaries. Extensive experiments were carried out on the ISPRS 2D Semantic Labeling Vaihingen data and GaoFen-2 data to demonstrate the effectiveness of our proposed method. Our method achieves better performance compared with other state-of-the-art methods.

Original languageEnglish
Article number3715
JournalRemote Sensing
Volume13
Issue number18
DOIs
Publication statusPublished - Sept 2021

Keywords

  • Deep learning
  • Land cover classification
  • Semantic segmentation

Fingerprint

Dive into the research topics of 'Dual attention feature fusion and adaptive context for accurate segmentation of very high-resolution remote sensing images'. Together they form a unique fingerprint.

Cite this

Shi, H., Fan, J., Wang, Y., & Chen, L. (2021). Dual attention feature fusion and adaptive context for accurate segmentation of very high-resolution remote sensing images. Remote Sensing, 13(18), Article 3715. https://doi.org/10.3390/rs13183715