EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Distribution-Aware CLIP-Adapter with Fine-Grained Text for Few-Shot Fine-Grained Classification

Jingming Chen, Zhaoyang Huang, Feng Wang, Zixiao Wen, Jingxing Zhu, Guangyao Zhou

Remote Sensing · 02.06.2026 · 18 (11) · 1813

DOI: 10.3390/rs18111813 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.06.2026. Verfasst von Jingming Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fine-Grained Few-Shot Classification (FG-FSC) in remote sensing has become a critical task, as the scarcity of high-quality annotated data severely restricts the performance of deep learning models in fine-grained classification. Although Contrastive Language-Image Pre-Training (CLIP) exhibits strong generalization ability in few-shot learning, it fails to generate discriminative text and image features when adapted to remote sensing tasks. In this paper, a framework is proposed to adapt CLIP to remote sensing FG-FSC from both visual and text aspects. First, we introduce a Distribution-AWare Adapter (DAWA) that adaptively fuses instance-level visual knowledge from few-shot samples with distribution-aware representations derived from Gaussian Discriminant Analysis based on the original CLIP zero-shot knowledge, leading to stable visual feature representations under various few-shot settings. A hybrid loss function that incorporates transductive and contrastive regularization is employed to further prevent overfitting and improve the discriminability of features. Furthermore, we generate category-level fine-grained text captions, optimizing the image–text alignment when extremely few training images are available. Experiments on multiple remote sensing and natural image datasets verify that the proposed framework achieves state-of-the-art few-shot fine-grained classification performance with a modest training cost, providing a practical solution for few-shot remote sensing image analysis.

Zitieren

APA

Chen, J., Huang, Z., Wang, F., Wen, Z., Zhu, J., & Zhou, G. (2026). Distribution-Aware CLIP-Adapter with Fine-Grained Text for Few-Shot Fine-Grained Classification. Remote Sensing, 18(11), 1813. https://doi.org/10.3390/rs18111813

Vancouver

Chen J, Huang Z, Wang F, Wen Z, Zhu J, Zhou G. Distribution-Aware CLIP-Adapter with Fine-Grained Text for Few-Shot Fine-Grained Classification. Remote Sensing. 2026;18(11):1813. doi:10.3390/rs18111813

BibTeX
@article{Chen2026,
  author = {Chen, Jingming and Huang, Zhaoyang and Wang, Feng and Wen, Zixiao and Zhu, Jingxing and Zhou, Guangyao},
  title = {Distribution-Aware CLIP-Adapter with Fine-Grained Text for Few-Shot Fine-Grained Classification},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1813},
  doi = {10.3390/rs18111813}
}
Kostenlos starten →