Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2504.06220 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912730116521984 |
|---|---|
| author | Hu, Xiaoxing Gong, Ziyang Wang, Yupei Jia, Yuru Lin, Fei Gao, Dexiang An, Ke Han, Jianhong Sun, Zhuoran Luo, Gen Luo, Gen Yang, Xue |
| author_facet | Hu, Xiaoxing Gong, Ziyang Wang, Yupei Jia, Yuru Lin, Fei Gao, Dexiang An, Ke Han, Jianhong Sun, Zhuoran Luo, Gen Luo, Gen Yang, Xue |
| contents | Parameter-Efficient Fine-Tuning (PEFT) is a technique that allows us to adapt powerful Foundation Models (FMs) to diverse downstream tasks while preserving and unleashing their inherent capabilities. However, we have observed that existing PEFT methods, which are often designed with natural imagery in mind, struggle when applied to Remote Sensing (RS) scenarios. This is primarily due to their inability to handle artifact influences, a problem particularly severe in RS image features. To tackle this challenge, we introduce Earth-Adapter, the first PEFT method specifically designed for RS artifacts conquering. Earth-Adapter introduces a novel Mixture of Frequency Adaptation process that combines a Mixture of Adapter (MoA) with Discrete Fourier Transformation (DFT). By utilizing DFT, Earth-Adapter can decompose features into different frequency components, precisely separating artifacts from original features. The MoA then dynamically assigns weights to each adapter expert, allowing for the combination of features across various frequency domains. These simple-yet-effective approaches enable Earth-Adapter to more efficiently overcome the disturbances caused by artifacts than previous PEFT methods, significantly enhancing the FMs' performance on RS scenarios. Experiments on Domain Adaptation (DA), and Domain Generalization (DG) semantic segmentation benchmarks showcase the Earth-Adapter's effectiveness. Compared with baseline Rein, Earth-Adapter significantly improves 9.0% mIoU in DA and 3.1% mIoU in DG benchmarks. Our code will be released at https://github.com/VisionXLab/Earth-Adapter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06220 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation Hu, Xiaoxing Gong, Ziyang Wang, Yupei Jia, Yuru Lin, Fei Gao, Dexiang An, Ke Han, Jianhong Sun, Zhuoran Luo, Gen Luo, Gen Yang, Xue Computer Vision and Pattern Recognition Parameter-Efficient Fine-Tuning (PEFT) is a technique that allows us to adapt powerful Foundation Models (FMs) to diverse downstream tasks while preserving and unleashing their inherent capabilities. However, we have observed that existing PEFT methods, which are often designed with natural imagery in mind, struggle when applied to Remote Sensing (RS) scenarios. This is primarily due to their inability to handle artifact influences, a problem particularly severe in RS image features. To tackle this challenge, we introduce Earth-Adapter, the first PEFT method specifically designed for RS artifacts conquering. Earth-Adapter introduces a novel Mixture of Frequency Adaptation process that combines a Mixture of Adapter (MoA) with Discrete Fourier Transformation (DFT). By utilizing DFT, Earth-Adapter can decompose features into different frequency components, precisely separating artifacts from original features. The MoA then dynamically assigns weights to each adapter expert, allowing for the combination of features across various frequency domains. These simple-yet-effective approaches enable Earth-Adapter to more efficiently overcome the disturbances caused by artifacts than previous PEFT methods, significantly enhancing the FMs' performance on RS scenarios. Experiments on Domain Adaptation (DA), and Domain Generalization (DG) semantic segmentation benchmarks showcase the Earth-Adapter's effectiveness. Compared with baseline Rein, Earth-Adapter significantly improves 9.0% mIoU in DA and 3.1% mIoU in DG benchmarks. Our code will be released at https://github.com/VisionXLab/Earth-Adapter. |
| title | Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.06220 |