Negative Margin Matters: Understanding Margin in Few-Shot Classification

Bin Liu, Yue Cao, Yutong Lin, Qi Li, Zheng Zhang, Mingsheng Long, Han Hu

ECCV 2020

doi:10.1007/978-3-030-58548-8_26 /eccv/2020/liu2020eccv-negative/

Abstract

In this paper, we unconventionally propose to adopt appropriate negative-margin to softmax loss for few-shot classification, which surprisingly works well for the open-set scenarios of few-shot classification. We then provide the intuitive explanation and the theoretical proof to understand why negative margin works well for few-shot classification. This claim is also demonstrated via sufficient experiments. With the negative-margin softmax loss, our approach achieves the state-of-the-art performance on all three standard benchmarks of few-shot classification. In the future, the negative margin may be applied in more general open-set scenarios that do not restrict the number of samples in novel classes.

PDF ECCV Semantic Scholar

Cite

Text

Liu et al. "Negative Margin Matters: Understanding Margin in Few-Shot Classification." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58548-8_26

Markdown

[Liu et al. "Negative Margin Matters: Understanding Margin in Few-Shot Classification." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/liu2020eccv-negative/) doi:10.1007/978-3-030-58548-8_26

BibTeX

@inproceedings{liu2020eccv-negative,
  title     = {{Negative Margin Matters: Understanding Margin in Few-Shot Classification}},
  author    = {Liu, Bin and Cao, Yue and Lin, Yutong and Li, Qi and Zhang, Zheng and Long, Mingsheng and Hu, Han},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58548-8_26},
  url       = {https://mlanthology.org/eccv/2020/liu2020eccv-negative/}
}