CMCap: Cross-Modal Meta-Captioning for Few-Shot Remote Sensing Image Captioning
IEEE Geoscience and Remote Sensing Letters · 2026 · 23 · 1-5
DOI: 10.1109/lgrs.2026.3674723 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Geoscience and Remote Sensing Letters, 2026. Verfasst von Kangda Cheng und 4 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Remote sensing image captioning (RSIC) aims to automatically generate natural language descriptions for remote sensing images, which holds significant application value. However, existing methods heavily rely on large-scale annotated datasets. In practical applications, due to the high annotation cost of remote sensing data and the dynamic diversity of ground object categories, only a limited number of labeled samples are available for many scenarios, leading to severe data scarcity challenges. To address this challenge, we propose the cross-modal meta-captioning (CMCap) framework. First, we design a sufficient task sampling (STS) strategy that constructs a large number of pseudo-tasks in each iteration to reduce gradient variance and improve data utilization. Then, we synthesize challenging support samples to enhance discriminative representation learning, and propose a task-adaptive cross-modal alignment (TCA) module to decouple task adaptability from general representation learning, thereby improving the model’s discriminability and cross-task generalization under extremely few-shot conditions. Moreover, we develop a meta-conditioning decoder that deeply fuses task context with query image features to guide a frozen large language model (LLM) in generating task-consistent captions. Experiments conducted on UCM-Captions, Sydney-Captions, and RSICD demonstrate that CMCap achieves competitive performance across various evaluation metrics and exhibits remarkable generalization capability under extreme data scarcity conditions.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Cheng, K., Liu, J., Mao, R., Wu, Z., & Cambria, E. (2026). CMCap: Cross-Modal Meta-Captioning for Few-Shot Remote Sensing Image Captioning. IEEE Geoscience and Remote Sensing Letters, 23, 1-5. https://doi.org/10.1109/lgrs.2026.3674723
Vancouver
Cheng K, Liu J, Mao R, Wu Z, Cambria E. CMCap: Cross-Modal Meta-Captioning for Few-Shot Remote Sensing Image Captioning. IEEE Geoscience and Remote Sensing Letters. 2026;23:1-5. doi:10.1109/lgrs.2026.3674723
BibTeX
@article{Cheng2026,
author = {Cheng, Kangda and Liu, Jinlong and Mao, Rui and Wu, Zhilu and Cambria, Erik},
title = {CMCap: Cross-Modal Meta-Captioning for Few-Shot Remote Sensing Image Captioning},
journal = {IEEE Geoscience and Remote Sensing Letters},
year = {2026},
volume = {23},
pages = {1--5},
doi = {10.1109/lgrs.2026.3674723}
}
EUVIMED