Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing

About

Remote sensing imagery, despite its broad applications in helping achieve Sustainable Development Goals and tackle climate change, has not yet benefited from the recent advancements of versatile, task-agnostic vision language models (VLMs). A key reason is that the large-scale, semantically diverse image-text dataset required for developing VLMs is still absent for remote sensing images. Unlike natural images, remote sensing images and their associated text descriptions cannot be efficiently collected from the public Internet at scale. In this work, we bridge this gap by using geo-coordinates to automatically connect open, unlabeled remote sensing images with rich semantics covered in OpenStreetMap, and thus construct SkyScript, a comprehensive vision-language dataset for remote sensing images, comprising 2.6 million image-text pairs covering 29K distinct semantic tags. With continual pre-training on this dataset, we obtain a VLM that surpasses baseline models with a 6.2% average accuracy gain in zero-shot scene classification across seven benchmark datasets. It also demonstrates the ability of zero-shot transfer for fine-grained object attribute classification and cross-modal retrieval. We hope this dataset can support the advancement of VLMs for various multi-modal tasks in remote sensing, such as open-vocabulary classification, retrieval, captioning, and text-to-image synthesis.

Zhecheng Wang, Rajanie Prabha, Tianyuan Huang, Jiajun Wu, Ram Rajagopal• 2023

Related benchmarks

TaskDatasetResultRank
Image-Text RetrievalRSICD--
26
Image-to-Text RetrievalRSITMD--
19
Text-to-Image RetrievalRSITMD--
19
Remote Sensing Image-Text RetrievalRSICD (test)
Text Retrieval R@16.59
14
Remote Sensing Image-Text RetrievalRSITMD (test)
Text Retrieval R@110.18
14
ClassificationResisc45 (test)
Top-1 Acc0.7094
12
Text-to-Image RetrievalUCM caption
R@1/5/1059.33
11
Health Outcome PredictionGeospatial Health Outcome Dataset (test)
Arthritis53
10
ClassificationSkyScript (test)
Top-1 Accuracy70.89
6
Image-to-Text RetrievalUCM Captions
Average Recall (R@1, R@5, R@10)72.22
5
Showing 10 of 11 rows

Other info

Follow for update