Joint Calibration for Semantic Segmentation

@article{Caesar2015JointCF,
  title={Joint Calibration for Semantic Segmentation},
  author={H. Caesar and J. Uijlings and V. Ferrari},
  journal={ArXiv},
  year={2015},
  volume={abs/1507.01581}
}
  • H. Caesar, J. Uijlings, V. Ferrari
  • Published 2015
  • Computer Science
  • ArXiv
  • Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects occur at multiple scales and therefore we should use regions at multiple scales. However, these regions are overlapping which creates conflicting class predictions at the pixel-level. (2) Class frequencies are highly imbalanced in realistic datasets. (3… CONTINUE READING
    26 Citations

    Figures, Tables, and Topics from this paper.

    Region-Based Semantic Segmentation with End-to-End Training
    • 20
    • Highly Influenced
    • PDF
    Region-Based Semantic Segmentation with End-to-End Training
    • 31
    • PDF
    Loss Max-Pooling for Semantic Image Segmentation
    • 75
    • PDF
    Learning from Weak and Noisy Labels for Semantic Segmentation
    • 56
    • PDF
    Edge-aware integration model for semantic labeling of rare classes
    • Liangjiang Yu, G. Fan
    • Computer Science
    • 2017 IEEE International Conference on Image Processing (ICIP)
    • 2017
    • 1
    A Network Structure to Explicitly Reduce Confusion Errors in Semantic Segmentation
    • 1
    • PDF
    Semantic labeling of aerial images by learning class-specific object proposals
    • M. Volpi, D. Tuia
    • Computer Science
    • 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
    • 2016
    • 1
    Controlled False Negative Reduction of Minority Classes in Semantic Segmentation
    • 2
    • PDF
    Scene segmentation with deep neural networks

    References

    SHOWING 1-10 OF 74 REFERENCES
    Weakly supervised semantic segmentation with a multi-image model
    • 162
    • PDF
    From image-level to pixel-level labeling with Convolutional Networks
    • 414
    • Highly Influential
    • PDF
    Learning to segment under various forms of weak supervision
    • 138
    • Highly Influential
    • PDF
    Learning Hierarchical Features for Scene Labeling
    • 2,116
    • Highly Influential
    • PDF
    Weakly supervised structured output learning for semantic segmentation
    • 161
    • PDF
    Simultaneous Detection and Segmentation
    • 869
    • Highly Influential
    • PDF
    Weakly supervised semantic segmentation for social images
    • 58
    • Highly Influential
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,929
    • Highly Influential
    • PDF
    Fusing Global and Local Scale for Semantic Image Segmentation
    • 50
    • Highly Influential
    • PDF