{"url":"/sota/self-supervised-learning-on-dabs","task":{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","note":null},"dataset":{"name":"DABS","url":"/dataset/dabs"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Self-Supervised Learning** is proposed for utilizing unlabeled data with the success of supervised learning. Producing a dataset with good labels is expensive, while unlabeled data is being generated all the time. The motivation of Self-Supervised Learning is to make use of the large amount of unlabeled data. The main idea of Self-Supervised Learning is to generate the labels from unlabeled data, according to the structure or characteristics of the data itself, and then train on this unsupervised data in a supervised manner. Self-Supervised Learning is wildly used in representation learning to make a model learn the latent features of the data. This technique is often employed in computer vision, video processing and robot control.\r\n\r\n\r\n<span class=\"description-source\">Source: [Self-supervised Point Set Local Descriptors for Point Cloud Registration ](https://arxiv.org/abs/2003.05199)</span>\r\n\r\nImage source: [LeCun](https://www.youtube.com/watch?v=7I0Qt7GALVk)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Images & Text","Med. Imaging","Natural Images","Sensors","Speech","Text"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Images & Text":null,"Med. Imaging":null,"Natural Images":null,"Sensors":null,"Speech":null,"Text":null}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Pretraining: None","metrics":{"Images & Text":"57.5","Med. Imaging":"68.1","Natural Images":"10.1","Sensors":"69.8","Speech":"24.9","Text":"42.3"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/dabs-a-domain-agnostic-benchmark-for-self","paper_url":"https://arxiv.org/abs/2111.12062v2","paper_title":"DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning","code":"https://github.com/alextamkin/dabs","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Pretraining: ShED","metrics":{"Images & Text":"54.3","Med. Imaging":"74.5","Natural Images":"20.9","Sensors":"88.7","Speech":"36.5","Text":"48.4"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/dabs-a-domain-agnostic-benchmark-for-self","paper_url":"https://arxiv.org/abs/2111.12062v2","paper_title":"DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning","code":"https://github.com/alextamkin/dabs","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Pretraining: e-Mix","metrics":{"Images & Text":"48.9","Med. Imaging":"72.4","Natural Images":"27.9","Sensors":"79.5","Speech":"41.8","Text":"44.1"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/dabs-a-domain-agnostic-benchmark-for-self","paper_url":"https://arxiv.org/abs/2111.12062v2","paper_title":"DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning","code":"https://github.com/alextamkin/dabs","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}