{"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/learning-from-context-agnostic-synthetic-data","title":"Towards Context-Agnostic Learning Using Synthetic Data","arxiv_id":"2005.14707","date":"2020-05-29","proceeding":"NeurIPS 2021 12","authors":["Charles Jin","Martin Rinard"],"abstract":"We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias and an error term, and exhibits a surprisingly weak dependence on the true labels. Inspired by these results, we present an algorithm aimed at minimizing the bias term by exploiting the ability to sample from each set independently. We apply our setting to visual classification tasks, where our approach enables us to train classifiers on datasets that consist entirely of a single synthetic example of each class. On several standard benchmarks for real-world image classification, we achieve robust performance in the context-agnostic setting, with good generalization to real world domains, whereas training directly on real world data without our techniques yields classifiers that are brittle to perturbations of the background.","url_abs":"https://arxiv.org/abs/2005.14707v3","url_pdf":"https://arxiv.org/pdf/2005.14707v3.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":"learning-from-context-agnostic-synthetic-data","repo_url":"https://github.com/charlesjin/synthetic_data","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"traffic-sign-recognition","task_name":"Traffic Sign Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.14707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14707"}},"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/charlesjin/synthetic_data","reach":null}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"96f1e718682ea419","entry":"Classifier","repo":"charlesjin/synthetic_data","repo_kind":"official","path":"gtsrb/model.py","file_url":"https://github.com/charlesjin/synthetic_data/blob/HEAD/gtsrb/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96f1e718682ea419"}},{"code_sha256_prefix":"9567a4ea0e7baa05","entry":"Classify","repo":"charlesjin/synthetic_data","repo_kind":"official","path":"gtsrb/model.py","file_url":"https://github.com/charlesjin/synthetic_data/blob/HEAD/gtsrb/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9567a4ea0e7baa05"}},{"code_sha256_prefix":"645b8e308b44353c","entry":"Encoder","repo":"charlesjin/synthetic_data","repo_kind":"official","path":"gtsrb/model.py","file_url":"https://github.com/charlesjin/synthetic_data/blob/HEAD/gtsrb/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"645b8e308b44353c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}