Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.16433 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916703405867008 |
|---|---|
| author | Gunduboina, Hariseetharam Khan, Muhammad Haris Banerjee, Biplab |
| author_facet | Gunduboina, Hariseetharam Khan, Muhammad Haris Banerjee, Biplab |
| contents | In recent years, large-scale vision-language models (VLMs) like CLIP have gained attention for their zero-shot inference using instructional text prompts. While these models excel in general computer vision, their potential for domain generalization in remote sensing (RS) remains underexplored. Existing approaches enhance prompt learning by generating visual prompt tokens but rely on full-image features, introducing noise and background artifacts that vary within a class, causing misclassification. To address this, we propose FrogDogNet, a novel prompt learning framework integrating Fourier frequency filtering and self-attention to improve RS scene classification and domain generalization. FrogDogNet selectively retains invariant low-frequency components while eliminating noise and irrelevant backgrounds, ensuring robust feature representation across domains. The model first extracts significant features via projection and self-attention, then applies frequency-based filtering to preserve essential structural information for prompt learning. Extensive experiments on four RS datasets and three domain generalization tasks show that FrogDogNet consistently outperforms state-of-the-art prompt learning methods, demonstrating superior adaptability across domain shifts. Our findings highlight the effectiveness of frequency-based invariant feature retention in generalization, paving the way for broader applications. Our code is available at https://github.com/HariseetharamG/FrogDogNet |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16433 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote Sensing Gunduboina, Hariseetharam Khan, Muhammad Haris Banerjee, Biplab Computer Vision and Pattern Recognition In recent years, large-scale vision-language models (VLMs) like CLIP have gained attention for their zero-shot inference using instructional text prompts. While these models excel in general computer vision, their potential for domain generalization in remote sensing (RS) remains underexplored. Existing approaches enhance prompt learning by generating visual prompt tokens but rely on full-image features, introducing noise and background artifacts that vary within a class, causing misclassification. To address this, we propose FrogDogNet, a novel prompt learning framework integrating Fourier frequency filtering and self-attention to improve RS scene classification and domain generalization. FrogDogNet selectively retains invariant low-frequency components while eliminating noise and irrelevant backgrounds, ensuring robust feature representation across domains. The model first extracts significant features via projection and self-attention, then applies frequency-based filtering to preserve essential structural information for prompt learning. Extensive experiments on four RS datasets and three domain generalization tasks show that FrogDogNet consistently outperforms state-of-the-art prompt learning methods, demonstrating superior adaptability across domain shifts. Our findings highlight the effectiveness of frequency-based invariant feature retention in generalization, paving the way for broader applications. Our code is available at https://github.com/HariseetharamG/FrogDogNet |
| title | FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote Sensing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.16433 |