{"id":"W4317931247","doi":"10.34133/plantphenomics.0025","title":"Semi-Self-Supervised Learning for Semantic Segmentation in Images with Dense Patterns","year":2023,"lang":"en","type":"article","venue":"Plant Phenomics","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Saskatchewan","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Annotation; Dice; Focus (optics); Deep learning; Pattern recognition (psychology); Domain (mathematical analysis); Sørensen–Dice coefficient; Pixel; Image segmentation","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":[],"consensus_categories":[],"category_scores_codex":[0.0001162299,0.000100454,0.0001160635,0.00001420349,0.000107204,0.00005342969,0.00008913574,0.00004049655,0.00001998477],"category_scores_gemma":[0.00001005352,0.00003582619,0.00003192102,0.0001957024,0.000006665866,0.00008056717,0.0000237822,0.00007261324,0.00002808916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002007999,"about_ca_system_score_gemma":0.000003661934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001041681,"about_ca_topic_score_gemma":0.0009683107,"domain_scores_codex":[0.9993568,0.00002541625,0.0001209386,0.0001917677,0.00008068694,0.0002243862],"domain_scores_gemma":[0.9996757,0.0002030196,0.00004364113,0.00002127189,0.0000188671,0.00003748442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001341812,0.0001058905,0.6424249,0.00006021341,0.00003750084,0.00003299049,0.001365991,0.001179407,0.3390126,0.00004793944,0.00243868,0.01315971],"study_design_scores_gemma":[0.000976866,0.0004825557,0.9630945,0.0001002748,0.00004530814,0.00002517586,0.005646051,0.01106238,0.01205428,0.0001505557,0.005849691,0.0005123771],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989159,0.00001493035,0.00002134993,0.0004515112,0.00005479023,0.0002613413,0.00008227951,0.0001246932,0.0000732673],"genre_scores_gemma":[0.998154,0.00009436063,0.0001627598,0.0001048904,0.0001888078,0.00004324268,0.001082016,0.000001397241,0.0001684718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3269583,"threshold_uncertainty_score":0.146095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01513384835884752,"score_gpt":0.19940276792477,"score_spread":0.1842689195659225,"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."}}