{"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-recognition-by-predicting","title":"Few-Shot Image Recognition by Predicting Parameters from Activations","arxiv_id":"1706.03466","date":"2017-06-12","proceeding":"CVPR 2018 6","authors":["Siyuan Qiao","Chenxi Liu","Wei Shen","Alan Yuille"],"abstract":"In this paper, we are interested in the few-shot learning problem. In\nparticular, we focus on a challenging scenario where the number of categories\nis large and the number of examples per novel category is very limited, e.g. 1,\n2, or 3. Motivated by the close relationship between the parameters and the\nactivations in a neural network associated with the same category, we propose a\nnovel method that can adapt a pre-trained neural network to novel categories by\ndirectly predicting the parameters from the activations. Zero training is\nrequired in adaptation to novel categories, and fast inference is realized by a\nsingle forward pass. We evaluate our method by doing few-shot image recognition\non the ImageNet dataset, which achieves the state-of-the-art classification\naccuracy on novel categories by a significant margin while keeping comparable\nperformance on the large-scale categories. We also test our method on the\nMiniImageNet dataset and it strongly outperforms the previous state-of-the-art\nmethods.","url_abs":"http://arxiv.org/abs/1706.03466v3","url_pdf":"http://arxiv.org/pdf/1706.03466v3.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":"few-shot-image-recognition-by-predicting","repo_url":"https://github.com/joe-siyuan-qiao/FewShot-CVPR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"Category-agnostic mapping WRN","rank_in_archive_order":76,"of":105,"metrics":{"Accuracy":"59.60"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"Category-agnostic mapping WRN","rank_in_archive_order":72,"of":95,"metrics":{"Accuracy":"73.74"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.03466","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}