{"id":"W4292534109","doi":"10.1101/2022.08.09.503251","title":"Semi-Self-Supervised Learning for Semantic Segmentation in Images with Dense Patterns","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Saskatchewan","funders":"","keywords":"Computer science; Segmentation; Annotation; Artificial intelligence; Dice; Pattern recognition (psychology); Deep learning; Sørensen–Dice coefficient; Domain (mathematical analysis); Field (mathematics); Domain adaptation; Pixel; Image segmentation; Classifier (UML)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002115964,0.001230026,0.001104042,0.001247218,0.0004204013,0.001037903,0.002035054,0.00157107,0.001124765],"category_scores_gemma":[0.004288593,0.0006561758,0.001165874,0.001010437,0.001125309,0.001423099,0.001176257,0.001722588,0.0006326995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001417402,"about_ca_system_score_gemma":0.00135327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006938326,"about_ca_topic_score_gemma":0.01043736,"domain_scores_codex":[0.998906,0.0002560859,0.00006445805,0.0004645182,0.0001922428,0.0001167404],"domain_scores_gemma":[0.997584,0.0009563265,0.0003020687,0.0004890541,0.0005714916,0.00009705767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003852727,0.0002443406,0.002303642,0.0001826013,0.0001801373,0.0001377755,0.0001304413,0.750675,0.01580826,0.00189758,0.004496609,0.2235584],"study_design_scores_gemma":[0.0000060447,0.00002442532,0.0002338252,0.000005626704,0.000005412118,0.0000121808,0.00001055934,0.9949443,0.003391305,0.001125176,0.0002361277,0.000005052304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1103997,0.0004935941,0.8815533,0.000250642,0.00009374048,0.000157276,0.0005165745,0.005104247,0.001430831],"genre_scores_gemma":[0.7212223,0.000177115,0.2722924,0.0004207411,0.00006562476,0.0002455863,0.002777008,0.0003885023,0.00241082],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006938326,"threshold_uncertainty_score":0.01379591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01150583217344161,"score_gpt":0.2013717929321172,"score_spread":0.1898659607586756,"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."}}