{"id":"W4366819366","doi":"10.1371/journal.pone.0284449","title":"Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection","year":2023,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Mitacs","keywords":"Artificial intelligence; Computer science; Metric (unit); Context (archaeology); F1 score; Pattern recognition (psychology); Deep learning; Focus (optics); Object detection; Convolutional neural network; Artificial neural network; Aerial image; Task (project management); Aerial imagery; Machine learning; Computer vision; Cartography; Image (mathematics); Geography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001113366,0.0001631015,0.0002947344,0.0002081966,0.0001273814,0.00006954825,0.0004465453,0.00008245485,0.000001663486],"category_scores_gemma":[0.00007841307,0.0001614661,0.00006892278,0.001367394,0.00004554593,0.0002781956,0.0001870595,0.0001215101,0.000002178089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003709268,"about_ca_system_score_gemma":0.00002546035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006369583,"about_ca_topic_score_gemma":0.00001761165,"domain_scores_codex":[0.9985718,0.00006401694,0.0003224983,0.0004165579,0.0002828698,0.0003423008],"domain_scores_gemma":[0.9988842,0.0001889495,0.0002442331,0.0004211201,0.0001720955,0.00008940393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000197124,0.0001601497,0.00007330385,0.00008735864,0.00007337021,0.00000147285,0.0006755316,0.3314467,0.6595413,0.0002398715,0.00003749406,0.007466297],"study_design_scores_gemma":[0.0002799854,0.000316015,0.0007884527,0.00007835368,0.00002767211,0.000002344681,0.0000117875,0.856321,0.1413774,0.0006495037,0.00001206894,0.000135328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8013386,0.00007582439,0.1968226,0.000207455,0.0001407526,0.0008534104,0.000007445789,0.0005506973,0.000003223894],"genre_scores_gemma":[0.9493877,0.000009066187,0.05017024,0.00004249195,0.0002409103,0.0001031498,0.00001070577,0.00002506858,0.00001071667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5248743,"threshold_uncertainty_score":0.6584396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04199708950813311,"score_gpt":0.2735805231631422,"score_spread":0.2315834336550091,"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."}}