Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation

@article{Zhang2019PyramidGN,
  title={Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation},
  author={Chi Zhang and Guosheng Lin and Fayao Liu and Jiushuang Guo and Qingyao Wu and Rui Yao},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={9586-9594}
}
  • Chi Zhang, Guosheng Lin, +3 authors Rui Yao
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
    • One-shot image segmentation aims to undertake the segmentation task of a novel class with only one training image available. The difficulty lies in that image segmentation has structured data representations, which yields a many-to-many message passing problem. Previous methods often simplify it to a one-to-many problem by squeezing support data to a global descriptor. However, a mixed global representation drops the data structure and information of individual elements. In this paper, we… CONTINUE READING
    View on IEEE
    openaccess.thecvf.com
    36 Citations
    Highly Influential Citations
    10
    Background Citations
    18
    Methods Citations
    18
    Results Citations
    2
    36 Citations
    Citation Type

    Citation Type

    Few-Shot Semantic Segmentation with Democratic Attention Networks
    • 4
    • Highly Influenced
    • PDF
    Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation
    • 1
    • PDF
    Weakly-supervised Object Representation Learning for Few-shot Semantic Segmentation
    • PDF
    Objectness-Aware One-Shot Semantic Segmentation
    • 1
    • Highly Influenced
    • PDF
    Part-aware Prototype Network for Few-shot Semantic Segmentation
    • 8
    • Highly Influenced
    • PDF
    Meta Parsing Networks: Towards Generalized Few-shot Scene Parsing with Adaptive Metric Learning
    • 3
    CRNet: Cross-Reference Networks for Few-Shot Segmentation
    • 12
    • PDF
    Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings
    • 2
    • PDF
    CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence
    • PDF
    Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Inputs
    • 2
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 27 REFERENCES
    SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
    • 61
    • Highly Influential
    • PDF
    CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning
    • 70
    • PDF
    Attention-Based Multi-Context Guiding for Few-Shot Semantic Segmentation
    • 46
    • PDF
    DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    • 6,164
    • Highly Influential
    • PDF
    Attention-based Graph Neural Network for Semi-supervised Learning
    • 86
    • PDF
    Few-Shot Semantic Segmentation with Prototype Learning
    • 89
    • Highly Influential
    • PDF
    Few-Shot Learning with Graph Neural Networks
    • 416
    • PDF
    One-Shot Learning for Semantic Segmentation
    • 127
    • Highly Influential
    • PDF
    Attention Models in Graphs
    • 41
    • PDF
    GAKE: Graph Aware Knowledge Embedding
    • 53
    • PDF