Power Normalizing Second-Order Similarity Network for Few-Shot Learning

@article{Zhang2019PowerNS,
  title={Power Normalizing Second-Order Similarity Network for Few-Shot Learning},
  author={Hongguang Zhang and Piotr Koniusz},
  journal={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2019},
  pages={1185-1193}
}
  • Hongguang Zhang, Piotr Koniusz
  • Published in
    IEEE Winter Conference on…
    2019
  • Computer Science
  • Second-and higher-order statistics of data points have played an important role in advancing the state of the art on several computer vision problems such as the fine-grained image and scene recognition. However, these statistics need to be passed via an appropriate pooling scheme to obtain the best performance. Power Normalizations are non-linear activation units which enjoy probability-inspired derivations and can be applied in CNNs. In this paper, we propose a similarity learning network… CONTINUE READING
    2
    Twitter Mentions

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-9 OF 9 CITATIONS

    Few-shot Learning with Multi-scale Self-supervision

    VIEW 19 EXCERPTS
    CITES METHODS & BACKGROUND

    Few-shot Action Recognition via Improved Attention with Self-supervision

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND

    Few-Shot Learning via Saliency-Guided Hallucination of Samples

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND

    Learning to Compare Relation: Semantic Alignment for Few-Shot Learning

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    Bilinear Attention Networks for Person Retrieval

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Model Selection for Generalized Zero-shot Learning

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 44 REFERENCES

    A Deeper Look at Power Normalizations

    VIEW 10 EXCERPTS

    Learning to Compare: Relation Network for Few-Shot Learning

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Higher-Order Occurrence Pooling for Bags-of-Words: Visual Concept Detection.

    VIEW 4 EXCERPTS

    Prototypical Networks for Few-shot Learning

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Siamese Neural Networks for One-Shot Image Recognition

    • Gregory R. Koch
    • Computer Science
    • 2015
    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    [Et al].

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    Feature Generating Networks for Zero-Shot Learning

    VIEW 1 EXCERPT