MKF-NET: KAN-Enhanced Vision Transformer for Remote Sensing Image Segmentation
Source abstract
Abstract
Remote sensing images, which obtain surface information from aerial or satellite platforms, are of great significance in fields such as environmental monitoring, urban planning, agricultural management, and disaster response. However, due to the complex and diverse types of ground coverage and significant differences in spectral characteristics in remote sensing images, achieving high-quality semantic segmentation still faces many challenges, such as blurred target boundaries and difficulty in recognizing small-scale objects. To address these issues, this study proposes a novel deep learning model, MKF-NET. The fusion of KAN convolution and Vision Transformer (ViT), combined with the multi-scale feature extraction and dense connection mechanism, significantly improves the semantic segmentation performance of remote sensing images. Experiments were conducted on the LoveDA dataset to systematically evaluate the segmentation performance of MKF-NET and several existing traditional deep learning models (U-net, Unet++, Deeplabv3+, Transunet, and U-KAN). Experimental results show that MKF-NET performs best in many indicators: it achieved a pixel precision of 78.53%, a pixel accuracy of 79.19%, an average class accuracy of 76.50%, and an average intersection-over-union ratio of 64.31%; it provides efficient technical support for remote sensing image analysis.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrared Target Detection Methodologies · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, China
School of Low Altitude Equipment and Intelligent Control, Guangzhou Maritime University, Guangzhou 510000, China
Department of Electronic and Electrical Engineering, The University of Sheffield, Sheffield S10 2TN, UK
Faculty of Engineering, Universiti Malaya, Kuala Lumpur 50603, Malaysia
Funding
National Natural Science Foundation of China · Jiangsu Graduate Research and Practice Innovation Program
References (34)
Show source-provided references
1. Remote sensing applications: An overview
2. MAENet: Multiple attention encoder–decoder network for farmland segmentation of remote sensing images
3. A refined pyramid scene parsing network for polarimetric SAR image semantic segmentation in agricultural areas
4. Boundary enhancement semantic segmentation for building extraction from remote sensed image
5. Building extraction with vision transformer
6. Xu, C., Wang, J., Sang, Y., Li, K., Liu, J., and Yang, G. (2023). An effective deep learning model for monitoring mangroves: A case study of the Indus Delta. Remote Sens., 15.10.3390/rs15092220 ↗
7. Improved swin transformer-based semantic segmentation of postearthquake dense buildings in urban areas using remote sensing images10.1109/JSTARS.2022.3225150 ↗
8. Segmentation of remotely sensed images with fuzzy thresholding, and quantitative evaluation10.1080/01431160050029567 ↗
9. Design of an image edge detection filter using the Sobel operator10.1109/4.996 ↗
10. A computational approach to edge detection10.1109/TPAMI.1986.4767851 ↗
11. Survey on SVM and their application in image classification
12. Random forest10.17849/insm-47-01-31-39.1 ↗
13. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
14. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
15. Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., and Liang, J. (2018, January 20). Unet++: A nested u-net architecture for medical image segmentation. Proceedings of the International Workshop on Deep Learning in Medical Image Analysis, Granada, Spain.10.1007/978-3-030-00889-5_1 ↗
16. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗
17. Chen, L.-C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv.
18. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8–14). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_49 ↗
19. Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Soljačić, M., Hou, T.Y., and Tegmark, M. (2024). Kan: Kolmogorov-arnold networks. arXiv.
20. Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21–26). Pyramid scene parsing network. Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.660 ↗
21. Zhao, S., Feng, Z., Chen, L., and Li, G. (2023). DANet: A Semantic Segmentation Network for Remote Sensing of Roads Based on Dual-ASPP Structure. Electronics, 12.10.3390/electronics12153243 ↗
22. Jia, J., Song, J., Kong, Q., Yang, H., Teng, Y., and Song, X. (2023). Multi-Attention-Based Semantic Segmentation Network for Land Cover Remote Sensing Images. Electronics, 12.10.3390/electronics12061347 ↗
23. Attention is all you need
24. Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., and Zhou, Y. (2021). Transunet: Transformers make strong encoders for medical image segmentation. arXiv.
25. Liu, B., Li, B., Sreeram, V., and Li, S. (2024). MBT-UNet: Multi-Branch Transform Combined with UNet for Semantic Segmentation of Remote Sensing Images. Remote Sens., 16.10.3390/rs16152776 ↗
26. Li, C., Liu, X., Li, W., Wang, C., Liu, H., Liu, Y., Chen, Z., and Yuan, Y. (March, January 25). U-kan makes strong backbone for medical image segmentation and generation. Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA.
27. Wang, J., Zheng, Z., Ma, A., Lu, X., and Zhong, Y. (2021). LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation. arXiv.
28. A survey on image data augmentation for deep learning10.1186/s40537-019-0197-0 ↗
29. Wang, S., Korolija, I., and Rovas, D. (2022, January 22–25). Impact of traditional augmentation methods on window state detection. Proceedings of the CLIMA 2022 The 14th REHVA HVAC World Congress, Rotterdam, The Netherlands.
30. Milletari, F., Navab, N., and Ahmadi, S.-A. (2016, January 25–28). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.10.1109/3DV.2016.79 ↗
31. Do vision transformers see like convolutional neural networks?
32. A survey of visual transformers10.1109/TNNLS.2022.3227717 ↗
33. A survey of the vision transformers and their CNN-transformer based variants10.1007/s10462-023-10595-0 ↗
34. From cnn to transformer: A review of medical image segmentation models10.1007/s10278-024-00981-7 ↗