{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/assume-augment-and-learn-unsupervised-few","title":"Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation","arxiv_id":"1902.09884","date":"2019-02-26","proceeding":null,"authors":["Antreas Antoniou","Amos Storkey"],"abstract":"The field of few-shot learning has been laboriously explored in the\nsupervised setting, where per-class labels are available. On the other hand,\nthe unsupervised few-shot learning setting, where no labels of any kind are\nrequired, has seen little investigation. We propose a method, named Assume,\nAugment and Learn or AAL, for generating few-shot tasks using unlabeled data.\nWe randomly label a random subset of images from an unlabeled dataset to\ngenerate a support set. Then by applying data augmentation on the support set's\nimages, and reusing the support set's labels, we obtain a target set. The\nresulting few-shot tasks can be used to train any standard meta-learning\nframework. Once trained, such a model, can be directly applied on small\nreal-labeled datasets without any changes or fine-tuning required. In our\nexperiments, the learned models achieve good generalization performance in a\nvariety of established few-shot learning tasks on Omniglot and Mini-Imagenet.","url_abs":"http://arxiv.org/abs/1902.09884v3","url_pdf":"http://arxiv.org/pdf/1902.09884v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"unsupervised-few-shot-image-classification","task_name":"Unsupervised Few-Shot Image Classification"},{"task_slug":"unsupervised-few-shot-learning","task_name":"Unsupervised Few-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on","task":"Unsupervised Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"AAL","rank_in_archive_order":28,"of":28,"metrics":{"Accuracy":"37.67"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on-1","task":"Unsupervised Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"AAL","rank_in_archive_order":28,"of":28,"metrics":{"Accuracy":"49.18"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.09884","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}