# Unsupervised Few-shot Learning via Self-supervised Training

arXiv: https://arxiv.org/abs/1912.12178 · HTML: https://mlsanity.com/paper/1912.12178/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [Self-Attention Message Passing for Contrastive Few-Shot Learning](https://mlsanity.com/paper/2210.06339/) (2022)
- [Domain Adaptive Few-Shot Open-Set Learning](https://mlsanity.com/paper/2309.12814/) (2023)
- [Self-Supervised Class-Cognizant Few-Shot Classification](https://mlsanity.com/paper/2202.08149/) (2022)
- [Generalising via Meta-Examples for Continual Learning in the Wild](https://mlsanity.com/paper/2101.12081/) (2021)
- [Trainable Class Prototypes for Few-Shot Learning](https://mlsanity.com/paper/2106.10846/) (2021)
- [Few-Example Clustering via Contrastive Learning](https://mlsanity.com/paper/2207.04050/) (2022)

## Abstract (arXiv)

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.