Corpus ID: 208158460

Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

@article{Zhang2019ReliabilityDM,
  title={Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach},
  author={Bingfeng Zhang and Jimin Xiao and Yunchao Wei and Mingjie Sun and Kaizhu Huang},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.08039}
}
  • Bingfeng Zhang, Jimin Xiao, +2 authors Kaizhu Huang
  • Published in AAAI 2019
  • Computer Science
  • Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent state-of-the-art approaches propose to adopt two-step solutions, \emph{i.e. } 1) learn to generate pseudo pixel-level masks, and 2) engage FCNs to train the semantic segmentation networks with the pseudo masks. However, the two-step solutions usually employ many bells… CONTINUE READING

    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.

    References

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

    FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation

    • Jiwoon Ahn, Suha Kwak
    • Computer Science
    • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • 2018
    VIEW 14 EXCERPTS
    HIGHLY INFLUENTIAL

    Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Normalized Cut Loss for Weakly-Supervised CNN Segmentation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    On Regularized Losses for Weakly-supervised CNN Segmentation

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

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

    VIEW 9 EXCERPTS

    Deep Extreme Cut: From Extreme Points to Object Segmentation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL