{"id":"W4399984784","doi":"10.3390/jimaging10070152","title":"Efficient Wheat Head Segmentation with Minimal Annotation: A Generative Approach","year":2024,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Dice; Annotation; Deep learning; Context (archaeology); Generative model; Machine learning; Generative grammar; Pattern recognition (psychology); Image segmentation","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001114212,0.0008471576,0.0007278305,0.0006845111,0.0003019765,0.001028791,0.001673979,0.001407568,0.001678392],"category_scores_gemma":[0.002292145,0.0007745425,0.001151186,0.0006510129,0.001064523,0.001283851,0.001470975,0.001364955,0.0006558842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001163986,"about_ca_system_score_gemma":0.0009310356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00452864,"about_ca_topic_score_gemma":0.008037247,"domain_scores_codex":[0.9994703,0.0001336876,0.00002054517,0.000196054,0.0001121207,0.00006741464],"domain_scores_gemma":[0.9991232,0.0004353641,0.00008522414,0.0002115732,0.0001038348,0.00004073247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000144554,0.00005880643,0.001239052,0.00006285072,0.00004738705,0.0001225288,0.00009860159,0.9155618,0.01600081,0.008022401,0.001636916,0.05700426],"study_design_scores_gemma":[0.000003756982,0.00001495407,0.0001392639,0.000003960497,0.000004961384,0.00003082422,0.000007465156,0.9933781,0.002868588,0.003031039,0.0005109871,0.000006152217],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04425646,0.0002250911,0.9500485,0.0003624934,0.00004128544,0.00008729049,0.0003803487,0.001965541,0.002633031],"genre_scores_gemma":[0.7364327,0.0002368613,0.2549526,0.0006127102,0.00005089874,0.0001887455,0.001969776,0.0005161614,0.005039526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00452864,"threshold_uncertainty_score":0.009004593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01399958247406314,"score_gpt":0.2352962832839071,"score_spread":0.221296700809844,"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."}}