{"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/few-shot-image-classification-via-contrastive","title":"Few-Shot Image Classification via Contrastive Self-Supervised Learning","arxiv_id":"2008.09942","date":"2020-08-23","proceeding":null,"authors":["Jianyi Li","Guizhong Liu"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2008.09942v1","url_pdf":"https://arxiv.org/pdf/2008.09942v1.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":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised 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"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"repair","method_name":"Repair"}],"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":"CSSL","rank_in_archive_order":10,"of":28,"metrics":{"Accuracy":"54.17"},"uses_additional_data":true},{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on-1","task":"Unsupervised Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"CSSL","rank_in_archive_order":12,"of":28,"metrics":{"Accuracy":"68.91"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.09942","atlas_url":"https://app.syntology.ai/?focus=2008.09942","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}