{"id":"W3064678530","doi":"10.34133/2020/3521852","title":"Global Wheat Head Detection (GWHD) Dataset: A Large and Diverse Dataset of High-Resolution RGB-Labelled Images to Develop and Benchmark Wheat Head Detection Methods","year":2020,"lang":"en","type":"article","venue":"Plant Phenomics","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":262,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Biotechnology and Biological Sciences Research Council; Core Research for Evolutional Science and Technology; Ministry of Agriculture, Forestry and Fisheries; Association Nationale de la Recherche et de la Technologie; Agence Nationale de la Recherche","keywords":"Artificial intelligence; Computer science; Benchmarking; Head (geology); RGB color model; Benchmark (surveying); Metadata; Task (project management); Computer vision; Pattern recognition (psychology); Geography; Cartography; Biology; Engineering","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":[0.0003012505,0.0002095777,0.000295151,0.000014101,0.0002886798,0.00007333865,0.000149369,0.0001142254,0.00003372937],"category_scores_gemma":[0.0001011947,0.00009847243,0.00002467684,0.0004322145,0.00004246125,0.0002362378,0.0002812678,0.0001029969,0.000009808821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004454856,"about_ca_system_score_gemma":0.000008114466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001779258,"about_ca_topic_score_gemma":0.01168617,"domain_scores_codex":[0.9986683,0.00014377,0.0002920173,0.000468051,0.0001396802,0.0002881544],"domain_scores_gemma":[0.999414,0.0001345819,0.0001047051,0.00006989739,0.00005441251,0.0002224167],"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":[0.0007448011,0.0001161919,0.004782389,0.00005272788,0.00006418548,0.000008122568,0.0002490563,0.00002766835,0.8459576,0.00005561548,0.02098296,0.1269587],"study_design_scores_gemma":[0.00285155,0.002458394,0.4256898,0.0001311051,0.0003822921,0.0001895486,0.00208417,0.003769014,0.1256707,0.0004390497,0.43481,0.001524424],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9466489,0.0003541392,0.00133377,0.0008711918,0.0001663734,0.0003260036,0.05024454,0.00003828461,0.0000167897],"genre_scores_gemma":[0.9764886,0.0003368263,0.004327442,0.0007906135,0.0003467447,0.00001450174,0.01768838,0.000001926759,0.000004965285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7202869,"threshold_uncertainty_score":0.6521158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0292381629140189,"score_gpt":0.2639985499690716,"score_spread":0.2347603870550527,"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."}}