{"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/interventional-few-shot-learning","title":"Interventional Few-Shot Learning","arxiv_id":"2009.13000","date":"2020-09-28","proceeding":"NeurIPS 2020 12","authors":["Zhongqi Yue","Hanwang Zhang","Qianru Sun","Xian-Sheng Hua"],"abstract":"We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution of IFSL is orthogonal to existing fine-tuning and meta-learning based FSL methods, hence IFSL can improve all of them, achieving a new 1-/5-shot state-of-the-art on \\textit{mini}ImageNet, \\textit{tiered}ImageNet, and cross-domain CUB. Code is released at https://github.com/yue-zhongqi/ifsl.","url_abs":"https://arxiv.org/abs/2009.13000v2","url_pdf":"https://arxiv.org/pdf/2009.13000v2.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":"interventional-few-shot-learning","repo_url":"https://github.com/yue-zhongqi/ifsl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.13000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13000"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yue-zhongqi/ifsl","reach":null}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"80d03250d680ce18","entry":"BaseLearner","repo":"yue-zhongqi/ifsl","repo_kind":"official","path":"MTL/models/IFSL.py","file_url":"https://github.com/yue-zhongqi/ifsl/blob/HEAD/MTL/models/IFSL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80d03250d680ce18"}},{"code_sha256_prefix":"58b6b3ac9172e74e","entry":"FeatureProcessor","repo":"yue-zhongqi/ifsl","repo_kind":"official","path":"MTL/models/IFSL.py","file_url":"https://github.com/yue-zhongqi/ifsl/blob/HEAD/MTL/models/IFSL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58b6b3ac9172e74e"}},{"code_sha256_prefix":"a995592d285912a6","entry":"MultiBiLinearClassifier","repo":"yue-zhongqi/ifsl","repo_kind":"official","path":"MTL/models/IFSL.py","file_url":"https://github.com/yue-zhongqi/ifsl/blob/HEAD/MTL/models/IFSL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a995592d285912a6"}},{"code_sha256_prefix":"5786545c0070f508","entry":"MultiLinearClassifier","repo":"yue-zhongqi/ifsl","repo_kind":"official","path":"MTL/models/IFSL.py","file_url":"https://github.com/yue-zhongqi/ifsl/blob/HEAD/MTL/models/IFSL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5786545c0070f508"}},{"code_sha256_prefix":"b8d3413ce024aa94","entry":"distLinear","repo":"yue-zhongqi/ifsl","repo_kind":"official","path":"MTL/models/IFSL.py","file_url":"https://github.com/yue-zhongqi/ifsl/blob/HEAD/MTL/models/IFSL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b8d3413ce024aa94"}},{"code_sha256_prefix":"9717549112b9bf4d","entry":"DeconfoundedLearner","repo":"yue-zhongqi/ifsl","repo_kind":"official","path":"MTL/models/IFSL.py","file_url":"https://github.com/yue-zhongqi/ifsl/blob/HEAD/MTL/models/IFSL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9717549112b9bf4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}