Corpus ID: 208513455

Learning Semantic Correspondence Exploiting an Object-level Prior

@article{Lee2019LearningSC,
  title={Learning Semantic Correspondence Exploiting an Object-level Prior},
  author={Junghyup Lee and Dong-Han Kim and Won-Kyung Lee and Jean Ponce and Bumsub Ham},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.12914}
}
  • Junghyup Lee, Dong-Han Kim, +2 authors Bumsub Ham
  • Published in ArXiv 2019
  • Computer Science
  • We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category. We propose to use images annotated with binary foreground masks and subjected to synthetic geometric deformations to train a convolutional neural network (CNN) for this task. Using these masks as part of the supervisory signal provides an object-level prior for the semantic correspondence task and offers a good compromise… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 67 REFERENCES

    Neighbourhood Consensus Networks

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Articulated Human Detection with Flexible Mixtures of Parts

    • Yi Yang, Deva Ramanan
    • Computer Science, Medicine
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2013
    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features

    VIEW 12 EXCERPTS

    End-to-End Weakly-Supervised Semantic Alignment

    VIEW 21 EXCERPTS
    HIGHLY INFLUENTIAL

    Object-Aware Dense Semantic Correspondence

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Proposal Flow

    VIEW 13 EXCERPTS

    Towards Understanding Action Recognition

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    The Pascal Visual Object Classes (VOC) Challenge

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    One-shot learning of object categories

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL