DOCK: Detecting Objects by Transferring Common-Sense Knowledge

@inproceedings{Singh2018DOCKDO,
  title={DOCK: Detecting Objects by Transferring Common-Sense Knowledge},
  author={Krishna Vijay Kumar Singh and Santosh Kumar Divvala and Ali Farhadi and Yong Jae Lee},
  booktitle={ECCV},
  year={2018}
}
We present a scalable approach for Detecting Objects by transferring Common-sense Knowledge (DOCK) from source to target categories. In our setting, the training data for the source categories have bounding box annotations, while those for the target categories only have image-level annotations. Current state-of-the-art approaches focus on image-level visual or semantic similarity to adapt a detector trained on the source categories to the new target categories. In contrast, our key idea is to… CONTINUE READING
8
Twitter Mentions

References

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

Fast R-CNN

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

WORDNET: A Lexical Database for English

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

  • International Journal of Computer Vision
  • 2016
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Weakly Supervised Deep Detection Networks

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

ImageNet Large Scale Visual Recognition Challenge

  • International Journal of Computer Vision
  • 2014
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

The PASCAL Visual Object Classes Challenge

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

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

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Detector discovery in the wild: Joint multiple instance and representation learning

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2014
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL