{"id":"W3132571997","doi":"10.1007/978-3-030-68787-8_21","title":"A Two-Stage Unsupervised Deep Learning Framework for Degradation Removal in Ancient Documents","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Task (project management); Generative grammar; Stage (stratigraphy); Degradation (telecommunications); Generative adversarial network; Machine learning; Artificial neural network; State (computer science); Pattern recognition (psychology); Engineering; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001540033,0.0005400612,0.0006110056,0.001195238,0.0002798017,0.000894014,0.00229282,0.000422713,0.00005134198],"category_scores_gemma":[0.0005053417,0.0005604575,0.0001865761,0.001141429,0.0002770131,0.0008674236,0.00104247,0.001245064,0.00001740004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006187669,"about_ca_system_score_gemma":0.0005069316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003556372,"about_ca_topic_score_gemma":0.0001836162,"domain_scores_codex":[0.9954215,0.0001012107,0.0007323661,0.001889374,0.001030559,0.000824954],"domain_scores_gemma":[0.9971306,0.0008739666,0.0003512797,0.001048037,0.0004233563,0.0001727214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009387986,0.0000472081,0.00009254003,0.0000709911,0.000008886178,0.0001876096,0.0007190118,0.006555022,0.0004259763,0.05793107,0.000004097067,0.9339482],"study_design_scores_gemma":[0.0008525052,0.0002935741,0.0001063768,0.00171399,0.0000104648,0.0001062166,0.000002173834,0.659748,0.01019864,0.3217754,0.004054515,0.001138121],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005062599,0.0006135508,0.9951481,0.0003629727,0.0009323444,0.0008848283,0.000004933607,0.0002904579,0.001256506],"genre_scores_gemma":[0.02270904,0.00009382273,0.9748286,0.001434932,0.0002262625,0.0000738717,0.00003334414,0.00004535323,0.0005547898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9328101,"threshold_uncertainty_score":0.9996847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0216423433731212,"score_gpt":0.2846975088664345,"score_spread":0.2630551654933133,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}