Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.12673 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909790500814848 |
|---|---|
| author | Liu, YiTong Liu, TianZhu GU, YanFeng |
| author_facet | Liu, YiTong Liu, TianZhu GU, YanFeng |
| contents | Cross-view geo-localization aims to determine the geographical location of a query image by matching it against a gallery of images. This task is challenging due to the significant appearance variations of objects observed from variable views, along with the difficulty in extracting discriminative features. Existing approaches often rely on extracting features through feature map segmentation while neglecting spatial and semantic information. To address these issues, we propose the EVA02-based Multi-scale Frequency Attention Fusion (MFAF) method. The MFAF method consists of Multi-Frequency Branch-wise Block (MFB) and the Frequency-aware Spatial Attention (FSA) module. The MFB block effectively captures both low-frequency structural features and high-frequency edge details across multiple scales, improving the consistency and robustness of feature representations across various viewpoints. Meanwhile, the FSA module adaptively focuses on the key regions of frequency features, significantly mitigating the interference caused by background noise and viewpoint variability. Extensive experiments on widely recognized benchmarks, including University-1652, SUES-200, and Dense-UAV, demonstrate that the MFAF method achieves competitive performance in both drone localization and drone navigation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12673 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MFAF: An EVA02-Based Multi-scale Frequency Attention Fusion Method for Cross-View Geo-Localization Liu, YiTong Liu, TianZhu GU, YanFeng Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Cross-view geo-localization aims to determine the geographical location of a query image by matching it against a gallery of images. This task is challenging due to the significant appearance variations of objects observed from variable views, along with the difficulty in extracting discriminative features. Existing approaches often rely on extracting features through feature map segmentation while neglecting spatial and semantic information. To address these issues, we propose the EVA02-based Multi-scale Frequency Attention Fusion (MFAF) method. The MFAF method consists of Multi-Frequency Branch-wise Block (MFB) and the Frequency-aware Spatial Attention (FSA) module. The MFB block effectively captures both low-frequency structural features and high-frequency edge details across multiple scales, improving the consistency and robustness of feature representations across various viewpoints. Meanwhile, the FSA module adaptively focuses on the key regions of frequency features, significantly mitigating the interference caused by background noise and viewpoint variability. Extensive experiments on widely recognized benchmarks, including University-1652, SUES-200, and Dense-UAV, demonstrate that the MFAF method achieves competitive performance in both drone localization and drone navigation tasks. |
| title | MFAF: An EVA02-Based Multi-scale Frequency Attention Fusion Method for Cross-View Geo-Localization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.12673 |