Few-Shot Learning with Geometric Constraints

@article{Jung2020FewShotLW,
  title={Few-Shot Learning with Geometric Constraints},
  author={Honggyu Jung and Seong-Whan Lee},
  journal={IEEE transactions on neural networks and learning systems},
  year={2020}
}
  • Honggyu Jung, Seong-Whan Lee
  • Published in
    IEEE transactions on neural…
    2020
  • Computer Science, Medicine
  • In this article, we consider the problem of few-shot learning for classification. We assume a network trained for base categories with a large number of training examples, and we aim to add novel categories to it that have only a few, e.g., one or five, training examples. This is a challenging scenario because: 1) high performance is required in both the base and novel categories; and 2) training the network for the new categories with a few training examples can contaminate the feature space… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES

    Dynamic Few-Shot Visual Learning Without Forgetting

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Low-Shot Visual Recognition by Shrinking and Hallucinating Features

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Low-Shot Learning from Imaginary Data

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    ImageNet Large Scale Visual Recognition Challenge

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Data Augmentation-Based Joint Learning for Heterogeneous Face Recognition

    VIEW 1 EXCERPT

    Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

    VIEW 1 EXCERPT

    Deep Manifold Learning Combined With Convolutional Neural Networks for Action Recognition

    • Xin Chen, Jian Weng, Wei Lu, Jiaming Xu, Jiasi Weng
    • Computer Science, Medicine
    • IEEE Transactions on Neural Networks and Learning Systems
    • 2018

    Few-Shot Image Recognition by Predicting Parameters from Activations

    VIEW 3 EXCERPTS