{"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/dataset-augmentation-in-feature-space","title":"Dataset Augmentation in Feature Space","arxiv_id":"1702.05538","date":"2017-02-17","proceeding":null,"authors":["Terrance DeVries","Graham W. Taylor"],"abstract":"Dataset augmentation, the practice of applying a wide array of\ndomain-specific transformations to synthetically expand a training set, is a\nstandard tool in supervised learning. While effective in tasks such as visual\nrecognition, the set of transformations must be carefully designed,\nimplemented, and tested for every new domain, limiting its re-use and\ngenerality. In this paper, we adopt a simpler, domain-agnostic approach to\ndataset augmentation. We start with existing data points and apply simple\ntransformations such as adding noise, interpolating, or extrapolating between\nthem. Our main insight is to perform the transformation not in input space, but\nin a learned feature space. A re-kindling of interest in unsupervised\nrepresentation learning makes this technique timely and more effective. It is a\nsimple proposal, but to-date one that has not been tested empirically. Working\nin the space of context vectors generated by sequence-to-sequence models, we\ndemonstrate a technique that is effective for both static and sequential data.","url_abs":"http://arxiv.org/abs/1702.05538v1","url_pdf":"http://arxiv.org/pdf/1702.05538v1.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":"dataset-augmentation-in-feature-space","repo_url":"https://github.com/YeongHyeon/Sequence-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"dataset-augmentation-in-feature-space","repo_url":"https://github.com/kjm1559/ADAE_LSTM_Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dataset-augmentation-in-feature-space","repo_url":"https://github.com/kjm1559/lstm_autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.05538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.05538"}},"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/kjm1559/ADAE_LSTM_Autoencoder","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YeongHyeon/Sequence-Autoencoder","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kjm1559/lstm_autoencoder","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"ran":0,"repositories":2}},"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":"8482209ace15327b","entry":"autoencoder","repo":"kjm1559/ADAE_LSTM_Autoencoder","repo_kind":"listed","path":"source/models.py","file_url":"https://github.com/kjm1559/ADAE_LSTM_Autoencoder/blob/HEAD/source/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8482209ace15327b"}},{"code_sha256_prefix":"1775751be3fc3051","entry":"cut_func","repo":"kjm1559/lstm_autoencoder","repo_kind":"listed","path":"source/utils.py","file_url":"https://github.com/kjm1559/lstm_autoencoder/blob/HEAD/source/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1775751be3fc3051"}},{"code_sha256_prefix":"3bcfe45be7e953cc","entry":"decoder","repo":"kjm1559/ADAE_LSTM_Autoencoder","repo_kind":"listed","path":"source/models.py","file_url":"https://github.com/kjm1559/ADAE_LSTM_Autoencoder/blob/HEAD/source/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bcfe45be7e953cc"}},{"code_sha256_prefix":"95a332703fa7fdef","entry":"decoder","repo":"kjm1559/lstm_autoencoder","repo_kind":"listed","path":"source/models.py","file_url":"https://github.com/kjm1559/lstm_autoencoder/blob/HEAD/source/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95a332703fa7fdef"}},{"code_sha256_prefix":"3fc7c355739e2171","entry":"encoder","repo":"kjm1559/ADAE_LSTM_Autoencoder","repo_kind":"listed","path":"source/models.py","file_url":"https://github.com/kjm1559/ADAE_LSTM_Autoencoder/blob/HEAD/source/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fc7c355739e2171"}},{"code_sha256_prefix":"cbe6c38415dae3dc","entry":"encoder","repo":"kjm1559/lstm_autoencoder","repo_kind":"listed","path":"source/models.py","file_url":"https://github.com/kjm1559/lstm_autoencoder/blob/HEAD/source/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cbe6c38415dae3dc"}},{"code_sha256_prefix":"b647123aab34840e","entry":"penchar_parser","repo":"kjm1559/lstm_autoencoder","repo_kind":"listed","path":"source/utils.py","file_url":"https://github.com/kjm1559/lstm_autoencoder/blob/HEAD/source/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b647123aab34840e"}},{"code_sha256_prefix":"5917ceaaa6136079","entry":"repeat_vector","repo":"kjm1559/lstm_autoencoder","repo_kind":"listed","path":"source/models.py","file_url":"https://github.com/kjm1559/lstm_autoencoder/blob/HEAD/source/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5917ceaaa6136079"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}