Batch Decorrelation for Active Metric Learning

@article{Kumari2020BatchDF,
  title={Batch Decorrelation for Active Metric Learning},
  author={Priyadarshini Kumari and R. Goru and S. Chaudhuri},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10008}
}
  • Priyadarshini Kumari, R. Goru, +1 author S. Chaudhuri
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • We present an active learning strategy for training parametric models of distance metrics, given triplet-based similarity assessments: object $x_i$ is more similar to object $x_j$ than to $x_k$. In contrast to prior work on class-based learning, where the fundamental goal is classification and any implicit or explicit metric is binary, we focus on {\em perceptual} metrics that express the {\em degree} of (dis)similarity between objects. We find that standard active learning approaches degrade… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 31 REFERENCES
    Active Perceptual Similarity Modeling with Auxiliary Information
    • 3
    • Highly Influential
    • PDF
    Selecting Influential Examples: Active Learning with Expected Model Output Changes
    • 83
    • PDF
    Cost-Effective HITs for Relative Similarity Comparisons
    • 59
    • PDF
    Deep ranking: Triplet MatchNet for music metric learning
    • 21
    • PDF
    The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
    • 868
    • PDF
    BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
    • 45
    • PDF
    Active Learning for Convolutional Neural Networks: A Core-Set Approach
    • 254
    • PDF
    Adaptively Learning the Crowd Kernel
    • 205
    • Highly Influential
    • PDF
    Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
    • 28
    • PDF
    Active Discriminative Text Representation Learning
    • 53
    • PDF