{"url":"/task/unsupervised-pre-training","name":"Unsupervised Pre-training","slug":"unsupervised-pre-training","description_markdown":"Pre-training a neural network using unsupervised (self-supervised) auxiliary tasks on unlabeled data.","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":265,"papers_with_code":126,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/unsupervised-pre-training-on-measles","slug":"unsupervised-pre-training-on-measles","dataset":"Measles","dataset_url":null,"rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"15RDLs","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/unsupervised-pre-training-on-uci-measles","slug":"unsupervised-pre-training-on-uci-measles","dataset":"UCI measles","dataset_url":null,"rows_in_archive":3,"metrics":["Sensitivity","Sensitivity (VEB)"],"first_row_in_archive_order":{"model":null,"paper_title":"RMDL: Random Multimodel Deep Learning for Classification","paper_url":"/paper/rmdl-random-multimodel-deep-learning-for","paper_date":"2018-05-03","arxiv_id":"1805.01890","code_links":[{"title":"kk7nc/RMDL","url":"https://github.com/kk7nc/RMDL"}],"syntology":null}}],"datasets":[{"url":"/dataset/m2caiseg","name":"m2caiSeg","full_name":"","num_papers_in_archive":5},{"url":"/dataset/carlane-benchmark","name":"CARLANE Benchmark","full_name":"","num_papers_in_archive":4},{"url":"/dataset/gbusv","name":"GBUSV","full_name":"Gallbladder Ultrasound Videos","num_papers_in_archive":2},{"url":"/dataset/oadat","name":"OADAT","full_name":"OADAT: Experimental and Synthetic Clinical Optoacoustic Data for Standardized Image Processing","num_papers_in_archive":2},{"url":"/dataset/icon645","name":"Icon645","full_name":"","num_papers_in_archive":1},{"url":"/dataset/seco","name":"SECO","full_name":"Seasonal Contrast","num_papers_in_archive":1},{"url":"/dataset/tyc-dataset","name":"TYC Dataset","full_name":"The TYC Dataset for Understanding Instance-Level Semantics and Motions of Cells in Microstructures","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":126,"tagged_in_all":265,"items":[{"url":"/paper/tabtransformer-tabular-data-modeling-using","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","date":"2020-12-11","arxiv_id":"2012.06678","repositories_listed":12,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/leveraging-pre-trained-checkpoints-for","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","date":"2019-07-29","arxiv_id":"1907.12461","repositories_listed":7,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/wav2vec-unsupervised-pre-training-for-speech","title":"wav2vec: Unsupervised Pre-training for Speech Recognition","date":"2019-04-11","arxiv_id":"1904.05862","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/a-transformer-based-framework-for-1","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","date":"2020-10-06","arxiv_id":"2010.02803","repositories_listed":6,"syntology":{"n":32,"n_ran":5,"n_unverified":27,"n_pointer_only":2}},{"url":"/paper/seasonal-contrast-unsupervised-pre-training","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","date":"2021-03-30","arxiv_id":"2103.16607","repositories_listed":5,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/how-far-can-we-go-without-convolution","title":"How far can we go without convolution: Improving fully-connected networks","date":"2015-11-09","arxiv_id":"1511.02580","repositories_listed":5,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/spatiotemporal-contrastive-video","title":"Spatiotemporal Contrastive Video Representation Learning","date":"2020-08-09","arxiv_id":"2008.03800","repositories_listed":4,"syntology":null},{"url":"/paper/multilingual-constituency-parsing-with-self","title":"Multilingual Constituency Parsing with Self-Attention and Pre-Training","date":"2018-12-31","arxiv_id":"1812.11760","repositories_listed":4,"syntology":{"n":28,"n_ran":3,"n_unverified":25,"n_pointer_only":3}},{"url":"/paper/drop-your-decoder-pre-training-with-bag-of","title":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval","date":"2024-01-20","arxiv_id":"2401.11248","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/online-bag-of-visual-words-generation-for","title":"OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning","date":"2020-12-21","arxiv_id":"2012.11552","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/self-training-and-pre-training-are","title":"Self-training and Pre-training are Complementary for Speech Recognition","date":"2020-10-22","arxiv_id":"2010.11430","repositories_listed":3,"syntology":null},{"url":"/paper/seco-exploring-sequence-supervision-for","title":"SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning","date":"2020-08-03","arxiv_id":"2008.00975","repositories_listed":3,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/depthsplat-connecting-gaussian-splatting-and","title":"DepthSplat: Connecting Gaussian Splatting and Depth","date":"2024-10-17","arxiv_id":"2410.13862","repositories_listed":2,"syntology":{"n":16,"n_ran":8,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/foundation-policies-with-hilbert","title":"Foundation Policies with Hilbert Representations","date":"2024-02-23","arxiv_id":"2402.15567","repositories_listed":2,"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":16}},{"url":"/paper/rethinking-semi-supervised-learning-with","title":"Rethinking Semi-supervised Learning with Language Models","date":"2023-05-22","arxiv_id":"2305.13002","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/don-t-stop-pretraining-make-prompt-based-fine","title":"Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner","date":"2023-05-02","arxiv_id":"2305.01711","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/unsupervised-pre-training-of-graph","title":"Unsupervised pre-training of graph transformers on patient population graphs","date":"2022-07-21","arxiv_id":"2207.10603","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-pre-training-for-person-re","title":"Large-Scale Pre-training for Person Re-identification with Noisy Labels","date":"2022-03-30","arxiv_id":"2203.16533","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/reinforcement-learning-with-action-free-pre","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","date":"2022-03-25","arxiv_id":"2203.13880","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-pre-training-on-patient","title":"Unsupervised Pre-Training on Patient Population Graphs for Patient-Level Predictions","date":"2022-03-23","arxiv_id":"2203.12616","repositories_listed":2,"syntology":null},{"url":"/paper/ai-bind-improving-binding-predictions-for","title":"AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands","date":"2021-12-25","arxiv_id":"2112.13168","repositories_listed":2,"syntology":null},{"url":"/paper/randomrooms-unsupervised-pre-training-from","title":"RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection","date":"2021-08-17","arxiv_id":"2108.07794","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-learning-of-keypoint","title":"Learning of feature points without additional supervision improves reinforcement learning from images","date":"2021-06-15","arxiv_id":"2106.07995","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/pebble-feedback-efficient-interactive","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","date":"2021-06-09","arxiv_id":"2106.05091","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/a-large-scale-study-on-unsupervised","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","date":"2021-04-29","arxiv_id":"2104.14558","repositories_listed":2,"syntology":null},{"url":"/paper/pre-training-strategies-and-datasets-for","title":"Pre-training strategies and datasets for facial representation learning","date":"2021-03-30","arxiv_id":"2103.16554","repositories_listed":2,"syntology":null},{"url":"/paper/dobf-a-deobfuscation-pre-training-objective","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","date":"2021-02-15","arxiv_id":"2102.07492","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-semantic-segmentation-by","title":"Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals","date":"2021-02-11","arxiv_id":"2102.06191","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","repositories_listed":2,"syntology":null},{"url":"/paper/up-detr-unsupervised-pre-training-for-object","title":"UP-DETR: Unsupervised Pre-training for Object Detection with Transformers","date":"2020-11-18","arxiv_id":"2011.09094","repositories_listed":2,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}