{"id":"W2984179350","doi":"10.1117/12.2538012","title":"Using transfer learning technique for SAR automatic target recognition","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced SAR Imaging Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Synthetic aperture radar; Artificial intelligence; Computer science; Transfer of learning; Pattern recognition (psychology); Automatic target recognition; Convolutional neural network; Support vector machine; Novelty detection; Novelty; Deep learning; Contextual image classification; Scheme (mathematics); Machine learning; Image (mathematics); Mathematics","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":[0.000545999,0.0005545827,0.0004098975,0.0006526047,0.0002211307,0.0004344141,0.0007796729,0.0007801385,0.002932976],"category_scores_gemma":[0.0008244527,0.0001676889,0.0004929873,0.0006881725,0.0003558855,0.0008700971,0.0006789144,0.0008736794,0.001988108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003270619,"about_ca_system_score_gemma":0.0003734444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009670182,"about_ca_topic_score_gemma":0.0007762157,"domain_scores_codex":[0.9996591,0.00006037929,0.00001834831,0.00008753339,0.0001355974,0.00003901184],"domain_scores_gemma":[0.9997625,0.0000632978,0.00003044126,0.00005299438,0.00008137914,0.000009485669],"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":[0.0001141409,0.0001391717,0.0008992658,0.0001549844,0.00007472518,0.0001744821,0.00006238297,0.09985255,0.06150121,0.007356482,0.00388743,0.8257832],"study_design_scores_gemma":[0.000007294639,0.0001043116,0.0008017985,0.00001396318,0.00001577974,0.0001655661,0.00002173704,0.9570139,0.02959833,0.005970884,0.006268007,0.00001828579],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01094789,0.0004403306,0.9844572,0.0001050593,0.00008500636,0.0000423869,0.00005363825,0.001431274,0.002437328],"genre_scores_gemma":[0.5786167,0.0009088621,0.4070434,0.0003026771,0.0001583509,0.000220121,0.000715053,0.0001804021,0.01185451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002932976,"threshold_uncertainty_score":0.009811759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02358214655515534,"score_gpt":0.269053875957172,"score_spread":0.2454717294020167,"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."}}