{"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-from-imaginary-data","title":"Low-Shot Learning from Imaginary Data","arxiv_id":"1801.05401","date":"2018-01-16","proceeding":"CVPR 2018 6","authors":["Yu-Xiong Wang","Ross Girshick","Martial Hebert","Bharath Hariharan"],"abstract":"Humans can quickly learn new visual concepts, perhaps because they can easily\nvisualize or imagine what novel objects look like from different views.\nIncorporating this ability to hallucinate novel instances of new concepts might\nhelp machine vision systems perform better low-shot learning, i.e., learning\nconcepts from few examples. We present a novel approach to low-shot learning\nthat uses this idea. Our approach builds on recent progress in meta-learning\n(\"learning to learn\") by combining a meta-learner with a \"hallucinator\" that\nproduces additional training examples, and optimizing both models jointly. Our\nhallucinator can be incorporated into a variety of meta-learners and provides\nsignificant gains: up to a 6 point boost in classification accuracy when only a\nsingle training example is available, yielding state-of-the-art performance on\nthe challenging ImageNet low-shot classification benchmark.","url_abs":"http://arxiv.org/abs/1801.05401v2","url_pdf":"http://arxiv.org/pdf/1801.05401v2.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-from-imaginary-data","repo_url":"https://github.com/tiangeluo/fsl-global","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.05401","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}