{"id":"W2286284940","doi":"10.1016/j.ins.2016.01.004","title":"Vehicle detection from highway satellite images via transfer learning","year":2016,"lang":"en","type":"article","venue":"Information Sciences","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Transfer of learning; Detector; Artificial intelligence; Satellite; Aerial image; Computer vision; Domain (mathematical analysis); Key (lock); Coding (social sciences); Image (mathematics); Pattern recognition (psychology); Remote sensing; Real-time computing; Telecommunications","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":[0.0006532943,0.00009369027,0.00008307024,0.0001892043,0.0005385263,0.0006958414,0.0004890332,0.00004300065,0.00008249619],"category_scores_gemma":[0.00008984915,0.00006289632,0.00004239738,0.0005337367,0.0001707529,0.007050145,0.00004912228,0.00008673358,0.0007408775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003255385,"about_ca_system_score_gemma":0.00004995845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000719492,"about_ca_topic_score_gemma":0.00001085769,"domain_scores_codex":[0.9987528,0.00008338461,0.0002918411,0.0001813191,0.000468765,0.000221865],"domain_scores_gemma":[0.9993933,0.0002039857,0.0000880988,0.0001455885,0.00009403432,0.00007503619],"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":[0.000003443271,0.000003990378,0.000584743,0.000001718182,0.000002890147,3.507856e-7,0.002065871,0.0008365802,0.02922365,0.003379883,0.0000124342,0.9638845],"study_design_scores_gemma":[0.001609132,0.0003614042,0.06608947,0.00008601291,0.000008108557,0.00001649133,0.001299941,0.384768,0.2589144,0.007406581,0.2786576,0.0007828815],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07335846,0.00003374888,0.9200811,0.0009412555,0.0003140874,0.00006530282,0.0000013244,0.000280776,0.004923918],"genre_scores_gemma":[0.9925765,0.00003112238,0.006848398,0.0003677416,0.00003410631,0.000006873733,0.000001403797,0.000002208805,0.0001316718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9631016,"threshold_uncertainty_score":0.9522728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01523124286481185,"score_gpt":0.2300002545770082,"score_spread":0.2147690117121964,"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."}}