Few-Shot Image Recognition by Predicting Parameters from Activations

@article{Qiao2018FewShotIR,
  title={Few-Shot Image Recognition by Predicting Parameters from Activations},
  author={Siyuan Qiao and Chenxi Liu and Wei Shen and Alan L. Yuille},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={7229-7238}
}
  • Siyuan Qiao, Chenxi Liu, +1 author Alan L. Yuille
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • In this paper, we are interested in the few-shot learning problem. [...] Key Method Zero training is required in adaptation to novel categories, and fast inference is realized by a single forward pass. We evaluate our method by doing few-shot image recognition on the ImageNet dataset, which achieves the state-of-the-art classification accuracy on novel categories by a significant margin while keeping comparable performance on the large-scale categories. We also test our method on the MiniImageNet dataset and it…Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 178 CITATIONS

    A Two-Stage Approach to Few-Shot Learning for Image Recognition

    Self-Supervised Learning For Few-Shot Image Classification

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A Baseline for Few-Shot Image Classification

    VIEW 14 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Few-Shot Learning with Geometric Constraints

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS

    FILTER CITATIONS BY YEAR

    2017
    2020

    CITATION STATISTICS

    • 37 Highly Influenced Citations

    • Averaged 58 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 36 REFERENCES