{"id":"W4405751318","doi":"10.1016/j.iswa.2024.200468","title":"Unsupervised domain adaptation with self-training for weed segmentation","year":2024,"lang":"en","type":"article","venue":"Intelligent Systems with Applications","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina; University of Alberta; Saskatchewan Polytechnic","funders":"","keywords":"Adaptation (eye); Domain adaptation; Computer science; Segmentation; Weed; Artificial intelligence; Domain (mathematical analysis); Psychology; Agronomy; Mathematics; Biology; Neuroscience","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":[0.0001482757,0.0001505242,0.0001340461,0.00002020013,0.0002264393,0.0002056878,0.0001220472,0.00005989767,0.00001863616],"category_scores_gemma":[0.000001846341,0.00004905289,0.00004910854,0.0004900998,0.00002151906,0.0001346287,0.000007437885,0.00006406834,0.00005585812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005306405,"about_ca_system_score_gemma":0.00002280166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001842789,"about_ca_topic_score_gemma":0.0004483106,"domain_scores_codex":[0.9990292,0.00002707767,0.0002188166,0.0003350039,0.0001905284,0.0001993545],"domain_scores_gemma":[0.999477,0.0002002159,0.00006205439,0.00005992891,0.0001225407,0.00007828959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004173053,0.0007830903,0.003772727,0.001012819,0.001198463,0.00001614906,0.01937936,0.005020212,0.4659629,0.1484177,0.005727828,0.3482914],"study_design_scores_gemma":[0.0003642355,0.00100275,0.003750007,0.0004153333,0.0002011876,0.00009171036,0.03850915,0.007313619,0.00436294,0.0009941759,0.9423019,0.0006930361],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4239595,0.002192299,0.5519931,0.00328322,0.0003991574,0.01317343,0.0002893801,0.001684522,0.003025348],"genre_scores_gemma":[0.9864523,0.00001461891,0.004811605,0.00006050235,0.0006027291,0.007064829,0.000539955,0.000003770005,0.0004496429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.936574,"threshold_uncertainty_score":0.2000319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03332533739401652,"score_gpt":0.2393287264050437,"score_spread":0.2060033890110272,"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."}}