Structured Set Matching Networks for One-Shot Part Labeling

  title={Structured Set Matching Networks for One-Shot Part Labeling},
  author={Jonghyun Choi and J. Krishnamurthy and Aniruddha Kembhavi and Ali Farhadi},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  • Jonghyun Choi, J. Krishnamurthy, +1 author Ali Farhadi
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • Diagrams often depict complex phenomena and serve as a good test bed for visual and textual reasoning. However, understanding diagrams using natural image understanding approaches requires large training datasets of diagrams, which are very hard to obtain. Instead, this can be addressed as a matching problem either between labeled diagrams, images or both. This problem is very challenging since the absence of significant color and texture renders local cues ambiguous and requires global… CONTINUE READING
    Generalizing from a Few Examples
    • 37
    • Highly Influenced
    • Open Access
    Small Sample Learning in Big Data Era
    • 24
    • Open Access
    Partial Or Complete, That's The Question
    • 5
    • Open Access
    OSLNet: Deep Small-Sample Classification With an Orthogonal Softmax Layer
    • 2
    • Open Access


    Publications referenced by this paper.
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,100
    • Open Access
    Object Detection with Discriminatively Trained Part Based Models
    • 8,299
    • Open Access
    Matching Networks for One Shot Learning
    • 1,845
    • Highly Influential
    • Open Access
    Deep Visual-Semantic Alignments for Generating Image Descriptions
    • 1,512
    • Open Access
    Conditional Random Fields as Recurrent Neural Networks
    • 1,831
    • Open Access
    Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
    • 10,609
    • Highly Influential
    • Open Access
    Siamese Neural Networks for One-Shot Image Recognition
    • Gregory R. Koch
    • Computer Science
    • 2015
    • 1,266
    • Open Access
    Learning a similarity metric discriminatively, with application to face verification
    • 2,133
    • Open Access
    Spatial Transformer Networks
    • 2,960
    • Open Access
    One-shot learning of object categories
    • 1,780
    • Open Access