# Few-Shot Image Classification via Contrastive Self-Supervised Learning

arXiv: https://arxiv.org/abs/2008.09942 · HTML: https://mlsanity.com/paper/2008.09942/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2020.

## Built on by (most cited first, 5 of 5)

- [Ranking Distance Calibration for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2112.00260/) (2021)
- [Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning](https://mlsanity.com/paper/2112.10982/) (2021)
- [Self-Attention Message Passing for Contrastive Few-Shot Learning](https://mlsanity.com/paper/2210.06339/) (2022)
- [Trainable Class Prototypes for Few-Shot Learning](https://mlsanity.com/paper/2106.10846/) (2021)
- [Multi-Level Contrastive Learning for Few-Shot Problems](https://mlsanity.com/paper/2107.07608/) (2021)

## Abstract (arXiv)

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we propose a new paradigm of unsupervised few-shot learning to repair the deficiencies. We solve the few-shot tasks in two phases: meta-training a transferable feature extractor via contrastive self-supervised learning and training a classifier using graph aggregation, self-distillation and manifold augmentation. Once meta-trained, the model can be used in any type of tasks with a task-dependent classifier training. Our method achieves state of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification datasets, with an 8- 28% increase compared to the available unsupervised few-shot learning methods.