{"id":"W4295035272","doi":"10.1016/j.compag.2022.107355","title":"Dandelion segmentation with background transfer learning and RGB-attention module","year":2022,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Dandelion; Artificial intelligence; Computer science; Segmentation; Color space; Transfer of learning; RGB color model; Convolutional neural network; Computer vision; Image segmentation; Pattern recognition (psychology); Image (mathematics)","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":[0.0005108076,0.001398377,0.001302171,0.001924834,0.0008213421,0.001391368,0.002161392,0.001574469,0.01109347],"category_scores_gemma":[0.0005705049,0.0007151605,0.001351068,0.001732822,0.0004927684,0.00101254,0.001542614,0.001539684,0.004678993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107831,"about_ca_system_score_gemma":0.002038272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02039618,"about_ca_topic_score_gemma":0.02830967,"domain_scores_codex":[0.9995459,0.00002037148,0.00001968387,0.0001980188,0.0001048186,0.0001111601],"domain_scores_gemma":[0.9997613,0.00003145342,0.00001332246,0.00006009838,0.0001066766,0.0000271134],"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":[0.0002853279,0.0001821293,0.0009708476,0.000128642,0.0001002648,0.0001000093,0.00007120523,0.01482965,0.08189639,0.002750147,0.007031928,0.8916535],"study_design_scores_gemma":[0.00003466474,0.0001265162,0.003470169,0.00004588117,0.0001475906,0.0002373831,0.00005293208,0.7986298,0.1770161,0.004391437,0.01579895,0.00004869157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02424384,0.0008148663,0.9523898,0.0002352451,0.0002351524,0.0001894288,0.0006052431,0.01452254,0.006763873],"genre_scores_gemma":[0.2111663,0.0008660911,0.7533879,0.0007280185,0.0001164351,0.0002533663,0.003419233,0.00164048,0.02842209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02039618,"threshold_uncertainty_score":0.04055488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006885737492615301,"score_gpt":0.1889572476926403,"score_spread":0.182071510200025,"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."}}