Corpus ID: 195346999

Transferring Common-Sense Knowledge for Object Detection

@article{Singh2018TransferringCK,
  title={Transferring Common-Sense Knowledge for Object Detection},
  author={Krishna Kumar Singh and Santosh Kumar Divvala and Ali Farhadi and Yong Jae Lee},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.01077}
}
  • Krishna Kumar Singh, Santosh Kumar Divvala, +1 author Yong Jae Lee
  • Published 2018
  • Computer Science
  • ArXiv
  • We propose the idea of transferring common-sense knowledge from source categories to target categories for scalable object detection. [...] Key Method We acquire such common-sense cues automatically from readily-available knowledge bases without any extra human effort. On the challenging MS COCO dataset, we find that using common-sense knowledge substantially improves detection performance over existing transfer-learning baselines.Expand Abstract

    Citations

    Publications citing this paper.

    Analysing object detectors from the perspective of co-occurring object categories

    • Csaba Nemes, Sándor Jordán
    • Computer Science
    • 2018 9th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)
    • 2018
    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 46 REFERENCES

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

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Object-Graphs for Context-Aware Visual Category Discovery

    VIEW 2 EXCERPTS

    Object Classification with Adaptable Regions

    VIEW 2 EXCERPTS

    LSDA: Large Scale Detection through Adaptation

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    The Role of Context for Object Detection and Semantic Segmentation in the Wild

    VIEW 1 EXCERPT

    Semi-supervised Domain Adaptation with Instance Constraints

    VIEW 1 EXCERPT