{"id":"W2981798583","doi":"10.1109/access.2019.2948618","title":"SAR Target Recognition Based on Cross-Domain and Cross-Task Transfer Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced SAR Imaging Techniques","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Nanjing University; Nanjing University of Aeronautics and Astronautics; National Natural Science Foundation of China","keywords":"Computer science; Transfer of learning; Synthetic aperture radar; Artificial intelligence; Convolutional neural network; Task (project management); Automatic target recognition; Deep learning; Domain adaptation; Data modeling; Pattern recognition (psychology); Domain (mathematical analysis); Machine learning","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":[0.0001631893,0.0001730129,0.0001551321,0.0001064403,0.00007290878,0.0002273137,0.0001842735,0.00008949106,0.0001328264],"category_scores_gemma":[0.00002086006,0.0001848615,0.00004027061,0.0001202444,0.00005197444,0.0006653984,0.00001312994,0.0003213746,0.00007758907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005151097,"about_ca_system_score_gemma":0.000007734973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007387663,"about_ca_topic_score_gemma":0.000001241133,"domain_scores_codex":[0.9991563,0.00002657658,0.0001689478,0.0002527884,0.0001435353,0.0002518511],"domain_scores_gemma":[0.9996082,0.00007896956,0.00001652243,0.0002012468,0.00004180172,0.00005323186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002076045,0.00007438855,0.210464,0.0006072497,0.00004758679,0.00004405353,0.0004214295,0.6252561,0.1340877,0.00005299714,0.0008947687,0.02784213],"study_design_scores_gemma":[0.002644692,0.0002273323,0.03804262,0.0003887865,0.00001857819,0.00001395757,0.00001970011,0.1924671,0.7345137,0.01090239,0.01946125,0.001299915],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8233078,0.00005031358,0.1720696,0.0000214423,0.0002532873,0.0002117442,0.00002061628,0.00087322,0.003191942],"genre_scores_gemma":[0.9923569,0.00001713675,0.007205618,0.0001632168,0.00006768269,0.00001839149,0.00002575507,0.00006870404,0.00007660982],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.600426,"threshold_uncertainty_score":0.7538432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01525592694558079,"score_gpt":0.2970902342920459,"score_spread":0.2818343073464651,"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."}}