Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios

@article{Royer2020LocalizingGI,
  title={Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios},
  author={A. Royer and Christoph H. Lampert},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={1716-1725}
}
  • A. Royer, Christoph H. Lampert
  • Published 2020
  • Computer Science
  • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories. Orthogonal to this, many real-life object detection applications, for example in remote sensing, instead require dealing with large images that contain only a few small objects of a single class, scattered heterogeneously across the space. In addition, they are often subject to strict… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 40 REFERENCES
    Dynamic Zoom-in Network for Fast Object Detection in Large Images
    41
    You Only Look Once: Unified, Real-Time Object Detection
    8194
    Focal Loss for Dense Object Detection
    2093
    Scalable Object Detection Using Deep Neural Networks
    750
    Efficient Subwindow Search: A Branch and Bound Framework for Object Localization
    392
    An efficient divide-and-conquer cascade for nonlinear object detection
    53
    SSD: Single Shot MultiBox Detector
    7779
    Cascade R-CNN: Delving Into High Quality Object Detection
    572
    Microsoft COCO: Common Objects in Context
    9669