English

Unsupervised Few-shot Learning via Self-supervised Training

Computer Vision and Pattern Recognition 2019-12-30 v1 Machine Learning

Abstract

Learning from limited exemplars (few-shot learning) is a fundamental, unsolved problem that has been laboriously explored in the machine learning community. However, current few-shot learners are mostly supervised and rely heavily on a large amount of labeled examples. Unsupervised learning is a more natural procedure for cognitive mammals and has produced promising results in many machine learning tasks. In the current study, we develop a method to learn an unsupervised few-shot learner via self-supervised training (UFLST), which can effectively generalize to novel but related classes. The proposed model consists of two alternate processes, progressive clustering and episodic training. The former generates pseudo-labeled training examples for constructing episodic tasks; and the later trains the few-shot learner using the generated episodic tasks which further optimizes the feature representations of data. The two processes facilitate with each other, and eventually produce a high quality few-shot learner. Using the benchmark dataset Omniglot and Mini-ImageNet, we show that our model outperforms other unsupervised few-shot learning methods. Using the benchmark dataset Market1501, we further demonstrate the feasibility of our model to a real-world application on person re-identification.

Keywords

Cite

@article{arxiv.1912.12178,
  title  = {Unsupervised Few-shot Learning via Self-supervised Training},
  author = {Zilong Ji and Xiaolong Zou and Tiejun Huang and Si Wu},
  journal= {arXiv preprint arXiv:1912.12178},
  year   = {2019}
}

Comments

12 pages, 3 figures

R2 v1 2026-06-23T12:57:27.635Z