Paper
6 June 2024 FMAMPN: lightweight feature map attention multipath network for semantic segmentation of remote sensing image
Songqi Hou, Ying Yuan
Author Affiliations +
Proceedings Volume 13175, International Conference on Computer Network Security and Software Engineering (CNSSE 2024); 131750Z (2024) https://doi.org/10.1117/12.3031941
Event: 4th International Conference on Computer Network Security and Software Engineering (CNSSE 2024), 2024, Sanya, China
Abstract
Deep neural networks excel in remote sensing image semantic segmentation, but existing methods, despite their sophistication, often focus on channel and spatial dependencies within identical feature maps. This can lead to a uniform treatment of diverse feature maps, hindering information exchange and impacting model efficacy. To address this, we introduce Feature Map Attention, dynamically modulating weights based on interdependencies among various feature maps. This fosters connections and feature fusion, enhancing the model's capability to represent features. Importantly, this improvement comes with minimal additional computational expense. We also incorporate multipath skip connections, efficiently transmitting features at various scales from encoder to decoder, boosting overall model effectiveness. Our FMAMPN, a lightweight neural network, outperforms other state-of-the-art lightweight models across various datasets.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Songqi Hou and Ying Yuan "FMAMPN: lightweight feature map attention multipath network for semantic segmentation of remote sensing image", Proc. SPIE 13175, International Conference on Computer Network Security and Software Engineering (CNSSE 2024), 131750Z (6 June 2024); https://doi.org/10.1117/12.3031941
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Transformers

Semantics

Remote sensing

Convolution

Feature fusion

Image processing

Back to Top