{"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":"/task/unsupervised-pre-training/papers/3","list_of":"/task/unsupervised-pre-training","task":"Unsupervised Pre-training","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,265],"of":265,"counts":{"archive_papers_tagged":265,"with_a_code_link":126,"where_syntology_ran_a_sample":43,"not_listed_spam_title":0,"listed":265,"listed_where_code_ran":43,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":38,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":38,"listed_every_run_a_failure_of_syntologys_instrument":5,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/unsupervised-pre-training","prev":"/task/unsupervised-pre-training/papers/2","next":null,"papers":[{"url":null,"slug":"representation-learning-for-weakly-supervised","title":"Representation Learning for Weakly Supervised Relation Extraction","date":"2021-04-10","arxiv_id":"2105.00815","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-replacement-and-combination-for","title":"On Architectures and Training for Raw Waveform Feature Extraction in ASR","date":"2021-04-09","arxiv_id":"2104.04298","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximal-multiverse-learning-for-promoting","title":"Maximal Multiverse Learning for Promoting Cross-Task Generalization of Fine-Tuned Language Models","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pretraining-for-object-detection","title":"Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors","date":"2021-03-08","arxiv_id":"2103.04814","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-brief-summary-of-interactions-between-meta","title":"A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning","date":"2021-03-01","arxiv_id":"2103.00845","repositories_listed":0,"syntology":null},{"url":null,"slug":"coverage-as-a-principle-for-discovering-1","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","date":"2021-02-24","arxiv_id":"2102.13515","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-apc-bidirectional-autoregressive","title":"Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR","date":"2021-02-12","arxiv_id":"2102.06816","repositories_listed":0,"syntology":null},{"url":null,"slug":"at-bert-adversarial-training-bert-for-acronym","title":"AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21","date":"2021-01-11","arxiv_id":"2101.03700","repositories_listed":0,"syntology":null},{"url":null,"slug":"r-latte-attention-module-for-visual-control","title":"R-LAtte: Attention Module for Visual Control via Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-active-pre-training-for","title":"Unsupervised Active Pre-Training for Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-translation-pre-training-for-data-to-1","title":"Machine Translation Pre-training for Data-to-Text Generation - A Case Study in Czech","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-tuning-of-pre-trained-representations-1","title":"Bi-tuning of Pre-trained Representations","date":"2020-11-12","arxiv_id":"2011.06182","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-au-intensity-estimation-with","title":"Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning","date":"2020-11-03","arxiv_id":"2011.01864","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-pre-training-strategy-for-recommendation","title":"Pre-training Graph Transformer with Multimodal Side Information for Recommendation","date":"2020-10-23","arxiv_id":"2010.12284","repositories_listed":0,"syntology":null},{"url":null,"slug":"gibert-introducing-linguistic-knowledge-into","title":"GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method","date":"2020-10-23","arxiv_id":"2010.12532","repositories_listed":0,"syntology":null},{"url":null,"slug":"corruption-is-not-all-bad-incorporating","title":"Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring","date":"2020-10-13","arxiv_id":"2010.06137","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-training-for-biomedical","title":"Unsupervised Pre-training for Biomedical Question Answering","date":"2020-09-27","arxiv_id":"2009.12952","repositories_listed":0,"syntology":null},{"url":null,"slug":"ernie-at-semeval-2020-task-10-learning-word","title":"ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model","date":"2020-09-08","arxiv_id":"2009.03706","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-learning-for-sequence-to","title":"Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages","date":"2020-08-11","arxiv_id":"2008.04549","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-construction-of-asr-systems","title":"Weakly Supervised Construction of ASR Systems with Massive Video Data","date":"2020-08-04","arxiv_id":"2008.01300","repositories_listed":0,"syntology":null},{"url":null,"slug":"pclnet-a-practical-way-for-unsupervised-deep","title":"Unsupervised Deep Representation Learning and Few-Shot Classification of PolSAR Images","date":"2020-06-27","arxiv_id":"2006.15351","repositories_listed":0,"syntology":null},{"url":"/paper/measles-rash-image-detection-using-deep","slug":"measles-rash-image-detection-using-deep","title":"Measles Rash Identification Using Residual Deep Convolutional Neural Network","date":"2020-05-18","arxiv_id":"2005.09112","repositories_listed":0,"syntology":null},{"url":null,"slug":"lottery-hypothesis-based-unsupervised-pre","title":"Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning","date":"2020-04-21","arxiv_id":"2004.09817","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-text-representations-as-meta","title":"Pre-training Text Representations as Meta Learning","date":"2020-04-12","arxiv_id":"2004.05568","repositories_listed":0,"syntology":null},{"url":null,"slug":"author2vec-a-framework-for-generating-user","title":"Author2Vec: A Framework for Generating User Embedding","date":"2020-03-17","arxiv_id":"2003.11627","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-context-aware-spoken","title":"Transfer Learning for Context-Aware Spoken Language Understanding","date":"2020-03-03","arxiv_id":"2003.01305","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-trained-texture-aware-and","title":"Unsupervised Pre-trained, Texture Aware And Lightweight Model for Deep Learning-Based Iris Recognition Under Limited Annotated Data","date":"2020-02-20","arxiv_id":"2002.09048","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-vascular-structure-generation-for","title":"Synthetic vascular structure generation for unsupervised pre-training in CTA segmentation tasks","date":"2020-01-02","arxiv_id":"2001.00666","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-training-for-natural","title":"Unsupervised Pre-training for Natural Language Generation: A Literature Review","date":"2019-11-13","arxiv_id":"1911.06171","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-unsupervised-pre-training-and","title":"Combining Unsupervised Pre-training and Annotator Rationales to Improve Low-shot Text Classification","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-evaluation-of-active-learning","title":"Empirical Evaluation of Active Learning Techniques for Neural MT","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-narrativeqa-with-heuristic-pre","title":"Extractive NarrativeQA with Heuristic Pre-Training","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-umls-semantic-types-with-deep","title":"Recognizing UMLS Semantic Types with Deep Learning","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-traing-for-sequence-to","title":"Unsupervised pre-training for sequence to sequence speech recognition","date":"2019-10-28","arxiv_id":"1910.12418","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-umls-concepts-from-medical-text","title":"Extracting UMLS Concepts from Medical Text Using General and Domain-Specific Deep Learning Models","date":"2019-10-03","arxiv_id":"1910.01274","repositories_listed":0,"syntology":null},{"url":null,"slug":"smirl-surprise-minimizing-rl-in-entropic","title":"SMiRL: Surprise Minimizing RL in Entropic Environments","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-transfer-learning-for-hyperspectral","title":"Effective training of deep convolutional neural networks for hyperspectral image classification through artificial labeling","date":"2019-09-12","arxiv_id":"1909.05507","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-training-for-goal-oriented","title":"Cross-Domain Training for Goal-Oriented Conversational Agents","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-unsupervised-pre-training-and","title":"Exploiting Unsupervised Pre-training and Automated Feature Engineering for Low-resource Hate Speech Detection in Polish","date":"2019-06-17","arxiv_id":"1906.09325","repositories_listed":0,"syntology":null},{"url":null,"slug":"color-constancy-convolutional-autoencoder","title":"Color Constancy Convolutional Autoencoder","date":"2019-06-04","arxiv_id":"1906.01340","repositories_listed":0,"syntology":null},{"url":null,"slug":"uhh-lt-at-semeval-2019-task-6-supervised-vs","title":"UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-training-helps-to-conserve","title":"Unsupervised pre-training helps to conserve views from input distribution","date":"2019-05-30","arxiv_id":"1905.12889","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-random-label-memorization-for","title":"Leveraging Random Label Memorization for Unsupervised Pre-Training","date":"2018-11-05","arxiv_id":"1811.01640","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-interpolation-as-an-unsupervised","title":"Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation","date":"2018-09-21","arxiv_id":"1809.08317","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-belief-networks-based-feature-generation","title":"Deep Belief Networks Based Feature Generation and Regression for Predicting Wind Power","date":"2018-07-31","arxiv_id":"1807.11682","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-discriminative-model-for-video","title":"Deep Discriminative Model for Video Classification","date":"2018-07-22","arxiv_id":"1807.08259","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrimnet-semi-supervised-action-recognition","title":"DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks","date":"2018-01-22","arxiv_id":"1801.07230","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-for-deep-learning","title":"Post-training for Deep Learning","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"co-morbidity-exploration-on-wearables","title":"Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task Learning","date":"2017-12-27","arxiv_id":"1712.09527","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhance-visual-recognition-under-adverse","title":"Enhance Visual Recognition under Adverse Conditions via Deep Networks","date":"2017-12-20","arxiv_id":"1712.07732","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-relative-depth-learning-for","title":"Self-Supervised Relative Depth Learning for Urban Scene Understanding","date":"2017-12-13","arxiv_id":"1712.04850","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-pitfall-of-unsupervised-pre-training","title":"A Pitfall of Unsupervised Pre-Training","date":"2017-11-23","arxiv_id":"1712.01655","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovery-of-visual-semantics-by-unsupervised","title":"Discovery of Visual Semantics by Unsupervised and Self-Supervised Representation Learning","date":"2017-08-19","arxiv_id":"1708.05812","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-pitfall-of-unsupervised-pre-training-1","title":"A Pitfall of Unsupervised Pre-Training","date":"2017-03-13","arxiv_id":"1703.04332","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-training-with-seq2seq","title":"Unsupervised Pre-training With Seq2Seq Reconstruction Loss for Deep Relation Extraction Models","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-learning-with-truncated-gaussian","title":"Unsupervised Learning with Truncated Gaussian Graphical Models","date":"2016-11-15","arxiv_id":"1611.04920","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-ladder-networks","title":"Adversarial Ladder Networks","date":"2016-11-07","arxiv_id":"1611.02320","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-the-best-feature-learning-procedure","title":"What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures?","date":"2016-06-05","arxiv_id":"1606.01535","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-discriminative-features-with-class","title":"Learning Discriminative Features with Class Encoder","date":"2016-05-09","arxiv_id":"1605.02424","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-learning-of-deep-stacked-autoencoders","title":"Faster learning of deep stacked autoencoders on multi-core systems using synchronized layer-wise pre-training","date":"2016-03-09","arxiv_id":"1603.02836","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-deep-feature-extraction-for","title":"Unsupervised Deep Feature Extraction for Remote Sensing Image Classification","date":"2015-11-25","arxiv_id":"1511.08131","repositories_listed":0,"syntology":null},{"url":null,"slug":"convergence-of-gradient-based-pre-training-in","title":"Convergence of gradient based pre-training in Denoising autoencoders","date":"2015-02-12","arxiv_id":"1502.03537","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-non-linear-reconstruction-models-for","title":"Learning Non-Linear Reconstruction Models for Image Set Classification","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-autoencoding-improves-generative","title":"Temporal Autoencoding Improves Generative Models of Time Series","date":"2013-09-12","arxiv_id":"1309.3103","repositories_listed":0,"syntology":null}],"record_sha256":"de6721cf5d1e0627151ed409a02faf6e8fc4326ff745e0107c14d5d71e6c22a4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}