SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913810500026368 |
|---|---|
| author | Guo, Yulong Zhang, Zilun Shang, Yongheng Zhao, Tiancheng Deng, Shuiguang Yang, Yingchun Yin, Jianwei |
| author_facet | Guo, Yulong Zhang, Zilun Shang, Yongheng Zhao, Tiancheng Deng, Shuiguang Yang, Yingchun Yin, Jianwei |
| contents | The long-tail problem presents a significant challenge to the advancement of semantic segmentation in ultra-high-resolution (UHR) satellite imagery. While previous efforts in UHR semantic segmentation have largely focused on multi-branch network architectures that emphasize multi-scale feature extraction and fusion, they have often overlooked the importance of addressing the long-tail issue. In contrast to prior UHR methods that focused on independent feature extraction, we emphasize data augmentation and multimodal feature fusion to alleviate the long-tail problem. In this paper, we introduce SRMF, a novel framework for semantic segmentation in UHR satellite imagery. Our approach addresses the long-tail class distribution by incorporating a multi-scale cropping technique alongside a data augmentation strategy based on semantic reordering and resampling. To further enhance model performance, we propose a multimodal fusion-based general representation knowledge injection method, which, for the first time, fuses text and visual features without the need for individual region text descriptions, extracting more robust features. Extensive experiments on the URUR, GID, and FBP datasets demonstrate that our method improves mIoU by 3.33\%, 0.66\%, and 0.98\%, respectively, achieving state-of-the-art performance. Code is available at: https://github.com/BinSpa/SRMF.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19839 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation Guo, Yulong Zhang, Zilun Shang, Yongheng Zhao, Tiancheng Deng, Shuiguang Yang, Yingchun Yin, Jianwei Computer Vision and Pattern Recognition The long-tail problem presents a significant challenge to the advancement of semantic segmentation in ultra-high-resolution (UHR) satellite imagery. While previous efforts in UHR semantic segmentation have largely focused on multi-branch network architectures that emphasize multi-scale feature extraction and fusion, they have often overlooked the importance of addressing the long-tail issue. In contrast to prior UHR methods that focused on independent feature extraction, we emphasize data augmentation and multimodal feature fusion to alleviate the long-tail problem. In this paper, we introduce SRMF, a novel framework for semantic segmentation in UHR satellite imagery. Our approach addresses the long-tail class distribution by incorporating a multi-scale cropping technique alongside a data augmentation strategy based on semantic reordering and resampling. To further enhance model performance, we propose a multimodal fusion-based general representation knowledge injection method, which, for the first time, fuses text and visual features without the need for individual region text descriptions, extracting more robust features. Extensive experiments on the URUR, GID, and FBP datasets demonstrate that our method improves mIoU by 3.33\%, 0.66\%, and 0.98\%, respectively, achieving state-of-the-art performance. Code is available at: https://github.com/BinSpa/SRMF.git. |
| title | SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.19839 |