Effective Use of Synthetic Data for Urban Scene Semantic Segmentation

@article{Saleh2018EffectiveUO,
  title={Effective Use of Synthetic Data for Urban Scene Semantic Segmentation},
  author={F. Saleh and M. S. Aliakbarian and M. Salzmann and L. Petersson and Jose M. Alvarez},
  journal={ArXiv},
  year={2018},
  volume={abs/1807.06132}
}
  • F. Saleh, M. S. Aliakbarian, +2 authors Jose M. Alvarez
  • Published 2018
  • Computer Science
  • ArXiv
  • Training a deep network to perform semantic segmentation requires large amounts of labeled data. [...] Key Result Our experiments evidence the effectiveness of our approach on Cityscapes and CamVid with models trained on synthetic data only.Expand Abstract
    61 Citations

    Figures, Tables, and Topics from this paper.

    Spatially-Aware Domain Adaptation for Semantic Segmentation of Urban Scenes
    • 1
    Adapting Semantic Segmentation of Urban Scenes via Mask-Aware Gated Discriminator
    • 3
    • Highly Influenced
    A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
    • 26
    Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
    • 230
    • PDF
    Transferring and Regularizing Prediction for Semantic Segmentation
    Restricted Deformable Convolution-Based Road Scene Semantic Segmentation Using Surround View Cameras
    • 33
    • Highly Influenced
    • PDF
    Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels
    • 10
    • PDF

    References

    SHOWING 1-10 OF 52 REFERENCES
    The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
    • 842
    • Highly Influential
    • PDF
    ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes
    • Y. Chen, W. Li, L. Gool
    • Computer Science
    • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • 2018
    • 121
    • Highly Influential
    • PDF
    Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
    • 230
    • Highly Influential
    • PDF
    The Cityscapes Dataset for Semantic Urban Scene Understanding
    • 3,417
    • Highly Influential
    • PDF
    Bringing Background into the Foreground: Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation
    • 21
    • PDF
    Exploiting Saliency for Object Segmentation from Image Level Labels
    • 99
    • PDF
    Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation
    • 23
    • PDF
    Learning Hierarchical Features for Scene Labeling
    • 2,117
    • PDF
    No More Discrimination: Cross City Adaptation of Road Scene Segmenters
    • 122
    • PDF