Corpus ID: 53039724

Self-Erasing Network for Integral Object Attention

@inproceedings{Hou2018SelfErasingNF,
  title={Self-Erasing Network for Integral Object Attention},
  author={Qibin Hou and Peng-Tao Jiang and Yunchao Wei and Ming-Ming Cheng},
  booktitle={NeurIPS},
  year={2018}
}
  • Qibin Hou, Peng-Tao Jiang, +1 author Ming-Ming Cheng
  • Published in NeurIPS 2018
  • Computer Science
  • Recently, adversarial erasing for weakly-supervised object attention has been deeply studied due to its capability in localizing integral object regions. [...] Key Method In particular, SeeNet leverages two self-erasing strategies to encourage networks to use reliable object and background cues for learning to attention. In this way, integral object regions can be effectively highlighted without including much more background regions.Expand Abstract

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

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 25 CITATIONS

    Saliency Guided Self-attention Network for Weakly-supervised Semantic Segmentation

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Highly Efficient Salient Object Detection with 100K Parameters

    VIEW 1 EXCERPT
    CITES BACKGROUND

    DANet: Divergent Activation for Weakly Supervised Object Localization

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES

    Adversarial Complementary Learning for Weakly Supervised Object Localization

    VIEW 9 EXCERPTS

    Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach

    VIEW 9 EXCERPTS

    Learning Deep Features for Discriminative Localization

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    The Pascal Visual Object Classes Challenge: A Retrospective

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation

    VIEW 1 EXCERPT

    Tell Me Where to Look: Guided Attention Inference Network