Recurrent Scene Parsing with Perspective Understanding in the Loop

@article{Kong2018RecurrentSP,
  title={Recurrent Scene Parsing with Perspective Understanding in the Loop},
  author={S. Kong and Charless C. Fowlkes},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={956-965}
}
  • S. Kong, Charless C. Fowlkes
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • Objects may appear at arbitrary scales in perspective images of a scene, posing a challenge for recognition systems that process images at a fixed resolution. We propose a depth-aware gating module that adaptively selects the pooling field size in a convolutional network architecture according to the object scale (inversely proportional to the depth) so that small details are preserved for distant objects while larger receptive fields are used for those nearby. The depth gating signal is… CONTINUE READING
    54 Citations
    Pixel-Wise Attentional Gating for Scene Parsing
    • 13
    • PDF
    CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
    • 2
    • PDF
    SPGNet: Semantic Prediction Guidance for Scene Parsing
    • 33
    • PDF
    Rethinking Atrous Convolution for Semantic Image Segmentation
    • 1,814
    • PDF
    Encoder–decoder with double spatial pyramid for semantic segmentation
    • 1
    Variational Context-Deformable ConvNets for Indoor Scene Parsing
    • 1
    • PDF
    OCNet: Object Context Network for Scene Parsing
    • 137
    • PDF
    Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing
    • 1
    • PDF

    References

    SHOWING 1-10 OF 41 REFERENCES
    Deeper Depth Prediction with Fully Convolutional Residual Networks
    • 811
    • PDF
    DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    • 5,600
    • Highly Influential
    • PDF
    RefineNet : MultiPath Refinement Networks with Identity Mappings for High-Resolution Semantic Segmentation
    • 132
    • Highly Influential
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 7,713
    • PDF
    Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
    • 1,633
    • Highly Influential
    • PDF
    Attention to Scale: Scale-Aware Semantic Image Segmentation
    • 672
    • Highly Influential
    • PDF
    Pyramid Scene Parsing Network
    • 2,994
    • PDF
    Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
    • 270
    • PDF
    Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
    • 661
    • PDF
    Deep convolutional neural fields for depth estimation from a single image
    • 572
    • PDF