LiteRoadSegNet: A Lightweight Road Segmentation Framework with Semantic–Topological Contrastive Learning in High-Resolution Remote Sensing Imagery.
Saved in:
| Title: | LiteRoadSegNet: A Lightweight Road Segmentation Framework with Semantic–Topological Contrastive Learning in High-Resolution Remote Sensing Imagery. |
|---|---|
| Authors: | Wu, Tao1,2 (AUTHOR), Peng, Yu1,2 (AUTHOR), Qin, Jianxin1,2,3 (AUTHOR), Wan, Yiliang1,2 (AUTHOR) wanylir@hunnu.edu.cn, Hu, Yaling2,3 (AUTHOR) |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 10, p1664. 27p. |
| Subjects: | Remote sensing, Contrastive learning, Deep learning |
| Abstract: | Highlights: What are the main findings? A lightweight and deployment-oriented road segmentation framework is developed to achieve an effective balance between segmentation accuracy and computational efficiency (6.33 M parameters/26.38 GFLOPs) for high-resolution remote sensing imagery. A low-overhead topology-aware supervision strategy combined with test-time adaptation improves structural connectivity and enhances robust cross-region deployment without requiring additional retraining. What are the implications of the main findings? The results demonstrate that lightweight deep learning model can achieve a favorable balance between efficiency and structural preservation, making them well suited for large-scale remote sensing applications under resource-constrained environments. The proposed framework reduces the dependence on region-specific retraining and facilitates scalable and cost-effective deployment in heterogeneous and dynamically changing geospatial environments. Deploying deep learning models for high-resolution remote sensing image segmentation remains challenging in resource-constrained scenarios due to the high computational cost of dense prediction and the structural vulnerability of thin objects such as roads. To address these challenges, we propose LiteRoadSegNet, a lightweight and deployment-oriented segmentation framework that achieves a favorable balance among efficiency, accuracy, and structural preservation. The proposed model adopts a compact encoder–decoder architecture composed of a lightweight hierarchical vision transformer and a streamlined decoder, enabling efficient multi-scale feature representation under limited computational budgets. To enhance structural consistency without increasing inference overhead, we further design a low-cost semantic–topological dual-branch contrastive learning scheme which enhances feature discriminability and preserves road connectivity during training. In addition, to improve deployment robustness in cross-region scenarios, we incorporate a lightweight test-time adaptation strategy based on Adaptive Batch Normalization (AdaBN) and sliding-window inference. This strategy enables seamless adaptation to unlabeled target domains without requiring model retraining. Extensive experiments demonstrate that LiteRoadSegNet achieves competitive segmentation performance and superior topology preservation while maintaining a small model footprint and high inference efficiency, making it well suited for large-scale remote sensing applications under resource-constrained environments. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
