Learning to Map Nearly Anything

@article{Salem2019LearningTM,
  title={Learning to Map Nearly Anything},
  author={T. Salem and Connor Greenwell and Hunter L Blanton and Nathan B. Jacobs},
  journal={IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium},
  year={2019},
  pages={4803-4806}
}
  • T. Salem, Connor Greenwell, +1 author Nathan B. Jacobs
  • Published 2019
  • Computer Science
  • IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium
  • Looking at the world from above, it is possible to estimate many properties of a given location, including the type of land cover and the expected land use. Historically, such tasks have relied on relatively coarse-grained categories due to the diffi-culty of obtaining fine-grained annotations. In this work, we propose an easily extensible approach that makes it possible to estimate fine-grained properties from overhead imagery. In particular, we propose a cross-modal distillation strategy to… CONTINUE READING
    3 Citations

    Figures and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Learning a Dynamic Map of Visual Appearance
    Learning to Map the Visual and Auditory World
    Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks
    • 5
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 14 REFERENCES
    What Goes Where: Predicting Object Distributions from Above
    • 7
    • PDF
    Learning deep representations for ground-to-aerial geolocalization
    • 205
    • PDF
    Predicting Ground-Level Scene Layout from Aerial Imagery
    • 57
    • PDF
    A Multimodal Approach to Mapping Soundscapes
    • 12
    • PDF
    CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
    • 43
    • PDF
    Predicting Geo-informative Attributes in Large-Scale Image Collections Using Convolutional Neural Networks
    • 38
    • PDF
    Wide-Area Image Geolocalization with Aerial Reference Imagery
    • 111
    • Highly Influential
    • PDF
    Microsoft COCO: Common Objects in Context
    • 10,915
    • PDF
    Cross-View Image Geolocalization
    • 71
    • PDF
    Identity Mappings in Deep Residual Networks
    • 4,067
    • PDF