# Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation

arXiv: https://arxiv.org/abs/1902.09884 · HTML: https://mlsanity.com/paper/1902.09884/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2019.

## Built on by (most cited first, 24 of 24)

- [Free Lunch for Few-shot Learning: Distribution Calibration](https://mlsanity.com/paper/2101.06395/) (2021)
- [Context-enriched molecule representations improve few-shot drug discovery](https://mlsanity.com/paper/2305.09481/) (2023)
- [Self-Supervision Can Be a Good Few-Shot Learner](https://mlsanity.com/paper/2207.09176/) (2022)
- [Few-Shot Learning with Class Imbalance](https://mlsanity.com/paper/2101.02523/) (2021)
- [Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2101.09499/) (2021)
- [SPeCiaL: Self-Supervised Pretraining for Continual Learning](https://mlsanity.com/paper/2106.09065/) (2021)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback](https://mlsanity.com/paper/2107.14035/) (2021)
- [GeNIe: Generative Hard Negative Images Through Diffusion](https://mlsanity.com/paper/2312.02548/) (2023)
- [Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment](https://mlsanity.com/paper/2305.11439/) (2023)
- [BECLR: Batch Enhanced Contrastive Few-Shot Learning](https://mlsanity.com/paper/2402.02444/) (2024)
- [GDC- Generalized Distribution Calibration for Few-Shot Learning](https://mlsanity.com/paper/2204.05230/) (2022)
- [Online Unsupervised Learning of Visual Representations and Categories](https://mlsanity.com/paper/2109.05675/) (2021)
- [Self-Attention Message Passing for Contrastive Few-Shot Learning](https://mlsanity.com/paper/2210.06339/) (2022)
- [Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning](https://mlsanity.com/paper/2209.13635/) (2022)
- [Self-Supervised Class-Cognizant Few-Shot Classification](https://mlsanity.com/paper/2202.08149/) (2022)
- [DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks](https://mlsanity.com/paper/2503.09679/) (2025)
- [Trainable Class Prototypes for Few-Shot Learning](https://mlsanity.com/paper/2106.10846/) (2021)
- [Unsupervised Episode Generation for Graph Meta-learning](https://mlsanity.com/paper/2306.15217/) (2023)
- [Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language Detection](https://mlsanity.com/paper/2311.02025/) (2023)
- [MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning](https://mlsanity.com/paper/2408.13385/) (2024)
- [Image augmentation improves few-shot classification performance in plant disease recognition](https://mlsanity.com/paper/2208.12613/) (2022)
- [Neural Routing in Meta Learning](https://mlsanity.com/paper/2210.07932/) (2022)

## Abstract (arXiv)

The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are required, has seen little investigation. We propose a method, named Assume, Augment and Learn or AAL, for generating few-shot tasks using unlabeled data. We randomly label a random subset of images from an unlabeled dataset to generate a support set. Then by applying data augmentation on the support set's images, and reusing the support set's labels, we obtain a target set. The resulting few-shot tasks can be used to train any standard meta-learning framework. Once trained, such a model, can be directly applied on small real-labeled datasets without any changes or fine-tuning required. In our experiments, the learned models achieve good generalization performance in a variety of established few-shot learning tasks on Omniglot and Mini-Imagenet.