{"id":"W3209952223","doi":"10.3390/ai2040034","title":"A Performance Comparison and Enhancement of Animal Species Detection in Images with Various R-CNN Models","year":2021,"lang":"en","type":"article","venue":"AI","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Transportation of Ontario; University of Victoria","funders":"","keywords":"Computer science; Object detection; Convolutional neural network; Artificial intelligence; Object (grammar); Focus (optics); Wildlife; Range (aeronautics); Computer vision; Animal species; Class (philosophy); Machine learning; Pattern recognition (psychology); Ecology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001559438,0.001485557,0.0006226134,0.001354376,0.0002197216,0.0006321658,0.00108852,0.0009339231,0.001309064],"category_scores_gemma":[0.003006752,0.0002594534,0.0006396341,0.000746962,0.0002100731,0.001302399,0.0005742712,0.0005176231,0.0006767758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014973,"about_ca_system_score_gemma":0.000549918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01711641,"about_ca_topic_score_gemma":0.01973199,"domain_scores_codex":[0.9994895,0.00007384786,0.00004200463,0.0001438087,0.0001375532,0.0001131668],"domain_scores_gemma":[0.9991437,0.0002340763,0.00009505278,0.0001058178,0.0003649623,0.00005643013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002052634,0.0005244147,0.01736309,0.0007634257,0.0007650853,0.0004366535,0.0001012821,0.1820073,0.05495507,0.001006586,0.008684514,0.7313399],"study_design_scores_gemma":[0.00002469949,0.0005590829,0.007694792,0.00005907117,0.0001486802,0.0001909143,0.00004771159,0.9531247,0.03626698,0.0002629361,0.001587644,0.00003276412],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8436326,0.008707647,0.1216367,0.0006577636,0.0006730333,0.0002576859,0.001798161,0.008771896,0.01386452],"genre_scores_gemma":[0.9024949,0.002173816,0.08568387,0.0002223398,0.00006698896,0.00007993815,0.003362091,0.0001692897,0.005746643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01711641,"threshold_uncertainty_score":0.03403354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01933718262962719,"score_gpt":0.2562978702347038,"score_spread":0.2369606876050766,"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."}}