Corpus ID: 212747952

In Defense of Graph Inference Algorithms for Weakly Supervised Object Localization

@article{Rahimi2020InDO,
  title={In Defense of Graph Inference Algorithms for Weakly Supervised Object Localization},
  author={Amir Rahimi and Amirreza Shaban and Thalaiyasingam Ajanthan and Richard Hartley and Byron Boots},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.08375}
}
  • Amir Rahimi, Amirreza Shaban, +2 authors Byron Boots
  • Published 2020
  • Computer Science
  • ArXiv
  • Weakly Supervised Object Localization (WSOL) methods have become increasingly popular since they only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. Typically, a WSOL model is first trained to predict class generic objectness scores on an off-the-shelf fully supervised source dataset and then it is progressively adapted to learn the objects in the weakly supervised target dataset. In this work, we argue that learning only an… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES

    Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Soft Proposal Networks for Weakly Supervised Object Localization

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    Dissimilarity Coefficient Based Weakly Supervised Object Detection

    VIEW 1 EXCERPT

    Large-scale knowledge transfer for object localization in ImageNet

    VIEW 3 EXCERPTS

    C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

    • Fang Wan, Chang Liu, +3 authors Qixiang Ye
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019
    VIEW 16 EXCERPTS
    HIGHLY INFLUENTIAL

    Min-Entropy Latent Model for Weakly Supervised Object Detection

    VIEW 1 EXCERPT

    Weakly supervised object detection with convex clustering

    VIEW 1 EXCERPT

    Revisiting Knowledge Transfer for Training Object Class Detectors

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer

    VIEW 2 EXCERPTS