{"id":"W3032638656","doi":"10.1109/lgrs.2020.2993652","title":"MiNet: Efficient Deep Learning Automatic Target Recognition for Small Autonomous Vehicles","year":2020,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Underwater Vehicles and Communication Systems","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Computer science; Object detection; Artificial intelligence; Deep learning; Convolutional neural network; Automatic target recognition; Sonar; Transfer of learning; Computer vision; Synthetic aperture sonar; Cognitive neuroscience of visual object recognition; Object (grammar); Pattern recognition (psychology); Synthetic aperture radar","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":[0.0003989654,0.0008114456,0.000381942,0.0003059457,0.0002429202,0.0004724438,0.001853948,0.0006822129,0.001940208],"category_scores_gemma":[0.0008934461,0.0003953789,0.0005008061,0.0002885388,0.0003527162,0.001053383,0.0009279931,0.001314942,0.0009259401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008508559,"about_ca_system_score_gemma":0.001007712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006518277,"about_ca_topic_score_gemma":0.00880179,"domain_scores_codex":[0.9998494,0.00001533506,0.000006691166,0.00004934088,0.00005023101,0.00002906504],"domain_scores_gemma":[0.9998361,0.0000493939,0.00001881336,0.00002926888,0.00005020974,0.00001616439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003143718,0.0002195643,0.00297603,0.0001205961,0.0001173953,0.0001679389,0.00007173388,0.5816638,0.02432493,0.005937067,0.02771185,0.3563747],"study_design_scores_gemma":[0.000005962742,0.00002542229,0.0001028516,0.000002400226,0.000002663739,0.00001297612,0.000003033939,0.9957914,0.002380498,0.0007600855,0.000909976,0.000002699419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06511655,0.0005140207,0.9125045,0.0004616211,0.0001851901,0.0001530964,0.001013585,0.01643479,0.003616625],"genre_scores_gemma":[0.5894166,0.0003671367,0.3948341,0.000452705,0.00006986382,0.0003709132,0.003526483,0.0005702464,0.01039194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006518277,"threshold_uncertainty_score":0.01296067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02419095708272804,"score_gpt":0.2037430548582876,"score_spread":0.1795520977755596,"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."}}