Newest papers

Data-Driven Vision-Language Models for Remote Sensing: A survey

Yue Zhou, Shujun Zhao, Xue Yang, Ruigang Li, Tianwen Zhang, Mengcheng Lan, Chaofeng Chen, Lingfei Ma, Hongjie He, Ke Li · 2026 · IEEE Geoscience and Remote Sensing Magazine

DOI: 10.1109/mgrs.2026.3696441 · cited by 1 works (OpenAlex) · open-access PDF

Indonesian

Selama era deep learning, inovasi data dalam data remote sensing (RS) vision model terutama berfokus pada mengoptimalkan arsitektur jaringan untuk tugas-tugas spesifik dan melakukan pelatihan akhir-untuk-akhir visi. Namun, dengan munculnya era Vision-Language Models (VLMs), dibatasi oleh tuntutan sumber daya komputasi yang substansial, paradigma penelitian mainstream telah beralih menuju menyesuaikan arsitektur jaringan untuk tugas-tugas spesifik dan melakukan pelatihan akhir-untuk-akhir. Namun, dengan munculnya era Vision-Language Models (VLMs) ini menandai perubahan dalam jalur inovasi dari model-sentris ke data-sentris. Terlepas dari pentingnya data yang semakin meningkat, komunitas penelitian akademis masih kekurangan sistematis, survei data-sentris yang luas untuk membimbing para pen

Machine translation (Meta M2M100); the English original follows.

Abstract

During the deep learning era, innovations in remote sensing (RS) vision models primarily focused on optimizing network architectures for specific tasks and conducting end-to-end training. However, with the advent of the Vision-Language Models (VLMs) era, constrained by substantial computational resource demands, the mainstream research paradigm has shifted towards adapting general-purpose VLMs using RS vertical domain data for fine-tuning, rather than modifying their core architectures. This transition marks a change in the innovation pathway from model-centric to data-centric. Despite the increasing importance of data, the academic community still lacks a systematic, data-centric survey to guide researchers in constructing high-quality RS vision-language datasets for various application scenarios and in conducting effective model fine-tuning and performance evaluation based on these datasets. To address this gap, this paper presents a systematic review of the development status of RS datasets tailored for VLMs. It further provides a comprehensive practical guide for RS researchers in the large model era, covering the entire pipeline from data construction to fine-tuning and evaluation. This paper aims to encourage the academic community to build more diverse and higher-quality vision-language datasets for specialized RS sub-fields. Ultimately, the goal is to converge these efforts into a comprehensive RS vision-language corpus that offers extensive task coverage and a wide geographical distribution, thereby laying a solid data foundation for advancing towards general artificial intelligence in RS.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Remote sensing, Computer science, Meteorology, Environmental science, Geography, Geology

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange