cs.CVNov 10, 2026

Towards Text-Only Remote Sensing Scene Classification via Semantic Proxy

Authors: Xianping Ma, Kunlin Wu, Xiaofeng Liu, Xiaokang Zhang, Yuanxin Ye

Organizations: Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, China. · Society Hub, The Hong Kong University of Science and Technology (Guangzhou), China, Guangzhou 511453, China. · School of Artificial Intelligence, Wuhan University, Wuhan 430072, China.

Abstract

Remote sensing scene classification (RSSC) is traditionally formulated as a vision-centric problem, where inference relies on rich visual representations extracted from images. In this work, we revisit this assumption by introducing text-only RSSC, a new problem setting that investigates whether remote sensing scenes can be recognized using only textual semantic representations. To enable this study, we propose SeProRS, which reformulates RSSC as a text-only classification task through semantic proxy generation. Specifically, a vision-language model (VLM) is first employed to convert remote sensing images into textual descriptions, termed semantic proxies, which are then encoded by a text embedding model for scene classification. This decoupled pipeline provides a unified and reproducible benchmark for evaluating text-only scene understanding. Furthermore, we investigate representative prompting strategies and proxy generators, and analyze their impact on classification performance, text embedding behavior, cross-generator transferability, and efficiency. Extensive experiments on three well-known RSSC datasets show that semantic proxies can preserve substantial discriminative information, while also revealing inherent limitations of purely text-based scene understanding. This paper does not aim to replace image-based RSSC, but instead establishes a new research direction by quantifying the feasibility and boundaries of semantic proxy-based scene recognition. The proposed benchmark and analysis provide a foundation for future research on efficient and modality-reduced remote sensing scene understanding. The source code and datasets will be accessible at https://github.com/sstary/SSRS.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models

    Oct 6, 2026Dongchen Si, Di Wang, Mingzhen Xu +3Remote Sensing Image UnderstandingEfficient Multimodal Inference

  2. Enabling Training-Free Text-Based Remote Sensing Segmentation

    Feb 19, 2026Jose Sosa, Danila Rukhovich, Anis Kacem +1Text-Guided Image SegmentationRemote Sensing Image Segmentation

  3. MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation

    May 11, 2026Ziyi Wang, Xianping Ma, Ziyao Wang +2Remote Sensing Image UnderstandingRemote Sensing Image Captioning