Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling

@inproceedings{Uhrig2016PixelLevelEA,
  title={Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling},
  author={J. Uhrig and Marius Cordts and Uwe Franke and T. Brox},
  booktitle={GCPR},
  year={2016}
}
  • J. Uhrig, Marius Cordts, +1 author T. Brox
  • Published in GCPR 2016
  • Computer Science
  • Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel’s direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance… CONTINUE READING
    134 Citations
    Bridging Category-level and Instance-level Semantic Image Segmentation
    • 93
    • Highly Influenced
    • PDF
    Deep Watershed Transform for Instance Segmentation
    • M. Bai, R. Urtasun
    • Computer Science
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 297
    • Highly Influenced
    • PDF
    Understanding Convolution for Semantic Segmentation
    • 570
    • PDF
    Bounding Box Embedding for Single Shot Person Instance Segmentation
    • PDF
    Layered Embeddings for Amodal Instance Segmentation
    • PDF
    Proposal-Based Instance Segmentation With Point Supervision
    • 1
    Semantic Instance Segmentation via Deep Metric Learning
    • 130
    • PDF
    Semantic Instance Segmentation for Autonomous Driving
    • 46

    References

    SHOWING 1-10 OF 45 REFERENCES
    Monocular Object Instance Segmentation and Depth Ordering with CNNs
    • 128
    • Highly Influential
    • PDF
    Instance-Level Segmentation with Deep Densely Connected MRFs
    • 28
    • Highly Influential
    • PDF
    Towards unified depth and semantic prediction from a single image
    • 298
    • PDF
    Instance Segmentation of Indoor Scenes Using a Coverage Loss
    • 76
    • PDF
    Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
    • 688
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 9,047
    • Highly Influential
    • PDF
    Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
    • 488
    • PDF
    Instance-Aware Semantic Segmentation via Multi-task Network Cascades
    • Jifeng Dai, Kaiming He, Jian Sun
    • Computer Science
    • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2016
    • 795
    • PDF
    Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs
    • 128
    • PDF
    Proposal-Free Network for Instance-Level Object Segmentation
    • 178
    • PDF