Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 4;20(2):e0309997.
doi: 10.1371/journal.pone.0309997. eCollection 2025.

Class-aware feature attention-based semantic segmentation on hyperspectral images

Prabu Sevugan  1 , Venkatesan Rudhrakoti  2 , Tai-Hoon Kim  3 , Megala Gunasekaran  4 , Swarnalatha Purushotham  4 , Ravikumar Chinthaginjala  5 , Irfan Ahmad  6 , Kumar A  7
Affiliations

Class-aware feature attention-based semantic segmentation on hyperspectral images

Prabu Sevugan et al. PLoS One. .

Abstract

This research explores an innovative approach to segment hyperspectral images. Aclass-aware feature-based attention approach is combined with an enhanced attention-based network, FAttNet is proposed to segment the hyperspectral images semantically. It is introduced to address challenges associated with inaccurate edge segmentation, diverse forms of target inconsistency, and suboptimal predictive efficacy encountered in traditional segmentation networks when applied to semantic segmentation tasks in hyperspectral images. First, the class-aware feature attention procedure is used to improve the extraction and processing of distinct types of semantic information. Subsequently, the spatial attention pyramid is employed in a parallel fashion to improve the correlation between spaces and extract context information from images at different scales. Finally, the segmentation results are refined using the encoder-decoder structure. It enhances precision in delineating distinct land cover patterns. The findings from the experiments demonstrate that FAttNet exhibits superior performance compared to established semantic segmentation networks commonly used. Specifically, on the GaoFen image dataset, FAttNet achieves a higher mean intersection over union (MIoU) of 77.03% and a segmentation accuracy of 87.26% surpassing the performance of the existing network.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Feature-based attention network model.
Fig 2
Fig 2. Spatial attention module of FAttNet model summary.
Fig 3
Fig 3
Segmentation Result (a) Input image (b) Segmented image.
Fig 4
Fig 4. Epoch vs training and validation accuracy and loss.
See this image and copyright information in PMC

References

    1. Boulila W. (2019). A top-down approach for semantic segmentation of big remote sensing images. Earth Science Informatics, 12, 295–306.
    1. Xu H., Wang W., Wang S., Zhou W., Chen Q., & Peng W. (2023). PPNet: pooling position attention network for semantic segmentation. Multimedia Tools and Applications, 1–17.
    1. Zhang Y., Li Y., Chen J., Yang C., & Rolfe P. (2023). Fine-Grained Guided Model Fusion Network with Attention Mechanism for Infrared Small Target Segmentation. International Journal of Intelligent Systems, 2023.
    1. Zhao Q., Liu J., Li Y., & Zhang H. (2021). Semantic segmentation with attention mechanism for remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–13.
    1. Wang H., Wang Y., Zhang Q., Xiang S., & Pan C. (2017). Gated convolutional neural network for semantic segmentation in high-resolution images. Remote Sensing, 9(5), 446.

LinkOut - more resources