{"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/low-shot-learning-with-large-scale-diffusion","title":"Low-shot learning with large-scale diffusion","arxiv_id":"1706.02332","date":"2017-06-07","proceeding":"CVPR 2018 6","authors":["Matthijs Douze","Arthur Szlam","Bharath Hariharan","Hervé Jégou"],"abstract":"This paper considers the problem of inferring image labels from images when\nonly a few annotated examples are available at training time. This setup is\noften referred to as low-shot learning, where a standard approach is to\nre-train the last few layers of a convolutional neural network learned on\nseparate classes for which training examples are abundant. We consider a\nsemi-supervised setting based on a large collection of images to support label\npropagation. This is possible by leveraging the recent advances on large-scale\nsimilarity graph construction.\n  We show that despite its conceptual simplicity, scaling label propagation up\nto hundred millions of images leads to state of the art accuracy in the\nlow-shot learning regime.","url_abs":"http://arxiv.org/abs/1706.02332v3","url_pdf":"http://arxiv.org/pdf/1706.02332v3.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":"low-shot-learning-with-large-scale-diffusion","repo_url":"https://github.com/facebookresearch/low-shot-with-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (1-shot, novel)","model":"LSD (ResNet-50)","rank_in_archive_order":6,"of":7,"metrics":{"Top-5 Accuracy (%)":"57.7"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-1","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (2-shot, novel)","model":"LSD (ResNet-50)","rank_in_archive_order":7,"of":8,"metrics":{"Top-5 Accuracy (%)":"66.9"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-6","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (5-shot, all)","model":"LSD  (ResNet-50)","rank_in_archive_order":8,"of":8,"metrics":{"Top-5 Accuracy (%)":"73.8"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1706.02332","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}