Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection

@article{Wang2018TowardsHC,
  title={Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection},
  author={Keze Wang and Xiaopeng Yan and Dongyu Zhang and Lei Zhang and Liang Lin},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={1605-1613}
}
  • Keze Wang, Xiaopeng Yan, +2 authors Liang Lin
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision. [...] Key Method Specifically, our SSM process concentrates on automatically discovering and pseudo-labeling reliable region proposals for enhancing the object detector via the introduced cross image validation, i.e., pasting these proposals into different labeled images to comprehensively measure their values under…Expand Abstract
    14
    Twitter Mentions

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 16 CITATIONS

    A Weakly Supervised Strategy for Learning Object Detection on a Humanoid Robot

    VIEW 13 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A Simple Semi-Supervised Learning Framework for Object Detection

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Beyond Weakly Supervised: Pseudo Ground Truths Mining for Missing Bounding-Boxes Object Detection

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    Progressive Latent Models for Self-Learning Scene-Specific Pedestrian Detectors

    VIEW 1 EXCERPT
    CITES BACKGROUND

    A new algorithm for small moving target detection on dynamic water surface

    VIEW 1 EXCERPT
    CITES METHODS

    Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images

    VIEW 1 EXCERPT

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 44 REFERENCES

    Self-Paced Learning for Latent Variable Models

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Active Self-Paced Learning for Cost-Effective and Progressive Face Identification

    VIEW 4 EXCERPTS

    Multi-task Self-Supervised Visual Learning

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Weaklyand semi-supervised object detection with expectationmaximization algorithm

    • Z. Yan, J. Liang, W. Pan, J. Li, C. Zhang
    • [cs.CV],
    • 2017
    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Few-Example Object Detection with Model Communication

    Self Paced Deep Learning for Weakly Supervised Object Detection

    A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection

    VIEW 2 EXCERPTS

    Active Learning for Human Pose Estimation

    VIEW 1 EXCERPT