Few-Shot Learning With Class Imbalance-Reference-Cited by-同舟云学术

Few-Shot Learning With Class Imbalance

Author:

Ochal Mateusz¹^ORCID,Patacchiola Massimiliano²^ORCID,Vazquez Jose³^ORCID,Storkey Amos²^ORCID,Wang Sen⁴^ORCID

Affiliation:

1. School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, U.K.

2. School of Informatics, University of Edinburgh, Edinburgh, U.K.

3. SeeByte Ltd., Edinburgh, U.K.

4. I-X & the Department of Electrical and Electronic Engineering, Imperial College London, London, U.K.

Funder

EPSRC Centre for Doctoral Training in Robotics and Autonomous Systems

Engineering and Physical Sciences Research Council

SeeByte Ltd, Edinburgh, U.K.

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computer Science Applications,Artificial Intelligence

Link

Reference67 articles.

1. How sensitive are meta-learners to dataset imbalance?;ochal;Proc Int Conf Learn Representations Workshop Learn,0

2. How to train your MAMLL;antoniou;Proc Int Conf Learn Representations,0

4. Assume, augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation;antoniou,2019

5. Federated meta-learning with fast convergence and efficient communication;chen,2018

Cited by 9 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献