Learning Concept Embeddings with Combined Human-Machine Expertise

  title={Learning Concept Embeddings with Combined Human-Machine Expertise},
  author={Michael J. Wilber and I. Kwak and D. Kriegman and Serge J. Belongie},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  • Michael J. Wilber, I. Kwak, +1 author Serge J. Belongie
  • Published 2015
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • This paper presents our work on "SNaCK," a low-dimensional concept embedding algorithm that combines human expertise with automatic machine similarity kernels. Both parts are complimentary: human insight can capture relationships that are not apparent from the object's visual similarity and the machine can help relieve the human from having to exhaustively specify many constraints. We show that our SNaCK embeddings are useful in several tasks: distinguishing prime and nonprime numbers on MNIST… CONTINUE READING
    27 Citations
    Disentangling Nonlinear Perceptual Embeddings With Multi-Query Triplet Networks
    • 8
    • PDF
    Context Embedding Networks
    • 5
    • PDF
    Learning Universal Embeddings from Attributes
    Conditional Similarity Networks
    • 59
    • PDF
    Relative distance comparisons with confidence judgements
    • 2
    • PDF
    Fine-Grained Image Classification by Exploring Bipartite-Graph Labels
    • Feng Zhou, Yuanqing Lin
    • Computer Science
    • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2016
    • 75
    • PDF
    Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification
    • 33
    • PDF
    Active Ordinal Querying for Tuplewise Similarity Learning


    Cost-Effective HITs for Relative Similarity Comparisons
    • 60
    • PDF
    Jointly Learning Multiple Perceptual Similarities
    • 1
    • PDF
    Simultaneous Active Learning of Classifiers & Attributes via Relative Feedback
    • A. Biswas, D. Parikh
    • Computer Science
    • 2013 IEEE Conference on Computer Vision and Pattern Recognition
    • 2013
    • 87
    • PDF
    Multiview Triplet Embedding: Learning Attributes in Multiple Maps
    • 56
    • PDF
    FaceNet: A unified embedding for face recognition and clustering
    • 5,432
    • PDF
    Learning the easy things first: Self-paced visual category discovery
    • 174
    • PDF
    Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
    • 311
    • PDF
    Stochastic triplet embedding
    • 145
    • Highly Influential
    • PDF
    Online multimodal deep similarity learning with application to image retrieval
    • 131
    • PDF