{"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/dont-wait-just-weight-improving-unsupervised","title":"Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights","arxiv_id":null,"date":"2020-06-22","proceeding":null,"authors":["Linus Ericsson"],"abstract":"In the absence of large labelled datasets, self-supervised learning techniques\r\ncan boost performance by learning useful representations from unlabelled data,\r\nwhich is often more readily available. However, there is often a domain shift\r\nbetween the unlabelled collection and the downstream target problem data. We\r\nshow that by learning Bayesian instance weights for the unlabelled data, we\r\ncan improve the downstream classification accuracy by prioritising the most\r\nuseful instances. Additionally, we show that the training time can be reduced by\r\ndiscarding unnecessary datapoints. Our method, BetaDataWeighter is evaluated\r\nusing the popular self-supervised rotation prediction task on STL-10 and Visual\r\nDecathlon. We compare to related instance weighting schemes, both hand-designed\r\nheuristics and meta-learning, as well as conventional self-supervised learning.\r\nBetaDataWeighter achieves both the highest average accuracy and rank across\r\ndatasets, and on STL-10 it prunes up to 78% of unlabelled images without significant\r\nloss in accuracy, corresponding to over 50% reduction in training time.","url_abs":"https://arxiv.org/pdf/2006.12360.pdf","url_pdf":"https://arxiv.org/pdf/2006.12360.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":[],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"BDW","rank_in_archive_order":87,"of":117,"metrics":{"Percentage correct":"71.12"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"NN-Weighter","rank_in_archive_order":93,"of":117,"metrics":{"Percentage correct":"69.15"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"RotNet","rank_in_archive_order":96,"of":117,"metrics":{"Percentage correct":"68.19"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"L2RW","rank_in_archive_order":99,"of":117,"metrics":{"Percentage correct":"63.13"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"05f44bd69caf2963e7e883bc78881423cb56ebb30d9303b789336fd7055277a5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}