{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/meta-transfer-learning-for-few-shot-learning","title":"Meta-Transfer Learning for Few-Shot Learning","arxiv_id":"1812.02391","date":"2018-12-06","proceeding":"CVPR 2019 6","authors":["Qianru Sun","Yaoyao Liu","Tat-Seng Chua","Bernt Schiele"],"abstract":"Meta-learning has been proposed as a framework to address the challenging\nfew-shot learning setting. The key idea is to leverage a large number of\nsimilar few-shot tasks in order to learn how to adapt a base-learner to a new\ntask for which only a few labeled samples are available. As deep neural\nnetworks (DNNs) tend to overfit using a few samples only, meta-learning\ntypically uses shallow neural networks (SNNs), thus limiting its effectiveness.\nIn this paper we propose a novel few-shot learning method called meta-transfer\nlearning (MTL) which learns to adapt a deep NN for few shot learning tasks.\nSpecifically, \"meta\" refers to training multiple tasks, and \"transfer\" is\nachieved by learning scaling and shifting functions of DNN weights for each\ntask. In addition, we introduce the hard task (HT) meta-batch scheme as an\neffective learning curriculum for MTL. We conduct experiments using (5-class,\n1-shot) and (5-class, 5-shot) recognition tasks on two challenging few-shot\nlearning benchmarks: miniImageNet and Fewshot-CIFAR100. Extensive comparisons\nto related works validate that our meta-transfer learning approach trained with\nthe proposed HT meta-batch scheme achieves top performance. An ablation study\nalso shows that both components contribute to fast convergence and high\naccuracy.","url_abs":"http://arxiv.org/abs/1812.02391v3","url_pdf":"http://arxiv.org/pdf/1812.02391v3.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":"meta-transfer-learning-for-few-shot-learning","repo_url":"https://github.com/yaoyao-liu/meta-transfer-learning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"meta-transfer-learning-for-few-shot-learning","repo_url":"https://github.com/yaoyao-liu/mini-imagenet-tools","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way","task":"Few-Shot Image Classification","dataset":"FC100 5-way (1-shot)","model":"MTL","rank_in_archive_order":14,"of":22,"metrics":{"Accuracy":"45.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-2","task":"Few-Shot Image Classification","dataset":"FC100 5-way (10-shot)","model":"MTL","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"63.4"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-1","task":"Few-Shot Image Classification","dataset":"FC100 5-way (5-shot)","model":"MTL","rank_in_archive_order":20,"of":22,"metrics":{"Accuracy":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"MTL","rank_in_archive_order":73,"of":105,"metrics":{"Accuracy":"61.2"},"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":"MTL","rank_in_archive_order":69,"of":95,"metrics":{"Accuracy":"75.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.02391","atlas_url":"https://app.syntology.ai/?focus=1812.02391","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1812.02391"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1812.02391\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1812.02391"},"call":"get_concepts_for_paper(arxiv_id=\"1812.02391\")"}],"by_repo":[{"repo":"yaoyao-liu/meta-transfer-learning","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1910.03648"],"harvested_for_calls":[{"arxiv_id":"1910.03648","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.03648"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.03648\")"}]},{"repo":"yaoyao-liu/mini-imagenet-tools","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"aab0aabe299683081fd1fe6042d75b041fbba8f362d72edc64696e4054f62c43","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}