21
views
0
recommends
+1 Recommend
2 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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

      Preprint
      , , , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          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.

          Related collections

          Author and article information

          Journal
          20 December 2023
          Article
          2312.12856
          11504250-7df6-494b-ba2c-2a4665e98f85

          http://creativecommons.org/licenses/by-sa/4.0/

          History
          Custom metadata
          Accepted by AAAI 2024
          cs.CV cs.AI cs.LG

          Computer vision & Pattern recognition,Artificial intelligence
          Computer vision & Pattern recognition, Artificial intelligence

          Comments

          Comment on this article