TechRxiv

Domain Adaptation with Contrastive Learning for Object Detection in Satellite Imagery

Download (11.25 MB)
preprint
posted on 2023-12-07, 04:25 authored by Debojyoti BiswasDebojyoti Biswas, Jelena Tesic

State-of-the-art object detection methods applied to satellite and drone imagery largely fail to identify small and dense objects. One reason is the high variability of content in the overhead imagery due to the terrestrial region captured and the high variability of acquisition conditions. Another reason is that the number and size of objects in aerial imagery are very different than in the consumer data. In this work, we propose a small object detection pipeline that improves the feature extraction process by spatial pyramid pooling, cross-stage partial networks, heatmap-based region proposal network, and object localization and identification through a novel image difficulty score that adapts the overall focal loss measure based on the image difficulty. Next, we propose novel contrastive learning with progressive domain adaptation to produce domain-invariant features across aerial datasets using local and global components. We show we can alleviate the degradation of object identification in previously unseen datasets. We create a first-ever domain adaptation benchmark using contrastive learning for the object detection task in highly imbalanced satellite datasets with significant domain gaps and dominant small objects from existing satellite benchmarks—the proposed method results in up to a 7.4% increase in mAP performance measure over the best state-of-art. 

Funding

NAVAIR SBIR N68335- 18-C-0199

History

Email Address of Submitting Author

bishaldebojyoti@gmail.com

ORCID of Submitting Author

0000-0002-8842-0207

Submitting Author's Institution

Texas State University

Submitting Author's Country

  • United States of America

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC