{"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/unsupervised-meta-learning-via-few-shot-1","title":"Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning","arxiv_id":"2303.00996","date":"2023-03-02","proceeding":"6th Workshop on Meta-Learning at NeurIPS 2022 2022 11","authors":["Huiwon Jang","Hankook Lee","Jinwoo Shin"],"abstract":"Unsupervised meta-learning aims to learn generalizable knowledge across a distribution of tasks constructed from unlabeled data. Here, the main challenge is how to construct diverse tasks for meta-learning without label information; recent works have proposed to create, e.g., pseudo-labeling via pretrained representations or creating synthetic samples via generative models. However, such a task construction strategy is fundamentally limited due to heavy reliance on the immutable pseudo-labels during meta-learning and the quality of the representations or the generated samples. To overcome the limitations, we propose a simple yet effective unsupervised meta-learning framework, coined Pseudo-supervised Contrast (PsCo), for few-shot classification. We are inspired by the recent self-supervised learning literature; PsCo utilizes a momentum network and a queue of previous batches to improve pseudo-labeling and construct diverse tasks in a progressive manner. Our extensive experiments demonstrate that PsCo outperforms existing unsupervised meta-learning methods under various in-domain and cross-domain few-shot classification benchmarks. We also validate that PsCo is easily scalable to a large-scale benchmark, while recent prior-art meta-schemes are not.","url_abs":"https://arxiv.org/abs/2303.00996v1","url_pdf":"https://arxiv.org/pdf/2303.00996v1.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":[{"paper_slug":"unsupervised-meta-learning-via-few-shot-1","repo_url":"https://github.com/alinlab/psco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"cross-domain-few-shot","task_name":"Cross-Domain Few-Shot"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised 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":"PsCo","rank_in_archive_order":15,"of":28,"metrics":{"Accuracy":"46.70"},"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":"PsCo","rank_in_archive_order":15,"of":28,"metrics":{"Accuracy":"63.26"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.00996","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}