{"id":"W4385466031","doi":"10.1007/978-3-031-37742-6_19","title":"Wildfires Detection and Segmentation Using Deep CNNs and Vision Transformers","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Convolutional neural network; Fire detection; Transformer; Deep learning; Aerial imagery; Computer vision; Image segmentation; Pixel; Deep neural networks; Firefighting; Pattern recognition (psychology); Cartography; Geography; 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":[0.0002065565,0.0002021793,0.0001829546,0.0004032603,0.0001470505,0.0001208726,0.00008077138,0.0001689437,0.000002556977],"category_scores_gemma":[0.000007418977,0.000199061,0.00002817989,0.0001905667,0.0001545924,0.0002079886,0.00003293185,0.0002355892,0.000003226683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001309867,"about_ca_system_score_gemma":0.00001548789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004415196,"about_ca_topic_score_gemma":0.0003822105,"domain_scores_codex":[0.9990135,0.00000833327,0.0002091323,0.0003492329,0.0002352211,0.0001845546],"domain_scores_gemma":[0.9996965,0.0000795083,0.0000361381,0.0001044561,0.00002285536,0.00006055183],"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":[0.000004442869,0.00000104645,0.00002742711,0.0001042528,0.000007658398,0.000005355729,0.000749448,0.08730226,0.009418619,0.00001449637,3.327143e-7,0.9023647],"study_design_scores_gemma":[0.0001508118,0.00006314388,0.0005802481,0.0002112594,0.000008355456,0.00005771322,0.000001733762,0.9948241,0.002531544,0.001243196,0.00009599108,0.000231933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01815075,0.0002681965,0.9796082,0.00002616258,0.001326105,0.0002234382,0.00000233259,0.0001824775,0.0002122808],"genre_scores_gemma":[0.9939816,0.000206227,0.005555627,0.0000420591,0.0001442741,0.000003112882,0.000001936763,0.00003738201,0.00002779795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9758309,"threshold_uncertainty_score":0.8117471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01175150991333566,"score_gpt":0.2349760622017561,"score_spread":0.2232245522884204,"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."}}