{"id":"W2645827484","doi":"10.1109/ccece.2017.7946733","title":"Fusion of transfer learning features and its application in image classification","year":2017,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial intelligence; Transfer of learning; Computer science; Pattern recognition (psychology); Autoencoder; Convolutional neural network; Support vector machine; Contextual image classification; Fuse (electrical); Feature extraction; Machine learning; Feature learning; Deep learning; Feature vector; Feature (linguistics); Image (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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002669003,0.00005090085,0.00007197285,0.00006943053,0.0001571175,0.0001038349,0.0002653238,0.00003908574,0.000006688333],"category_scores_gemma":[0.00006354347,0.00004657346,0.0000145202,0.00006288699,0.00002691835,0.0004922077,0.00004818634,0.0001067541,0.00000694092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008058735,"about_ca_system_score_gemma":0.00001158571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003631416,"about_ca_topic_score_gemma":0.00003357312,"domain_scores_codex":[0.9994665,0.00003883367,0.0001208424,0.0001825383,0.000111674,0.00007961332],"domain_scores_gemma":[0.9996178,0.00003157684,0.00006108848,0.0002157506,0.00004507204,0.0000287008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0000138716,0.00003399761,0.008295274,0.00003050471,0.000003147235,0.000001162211,0.002607004,0.0001704142,0.4118001,0.3286984,0.00002549227,0.2483206],"study_design_scores_gemma":[0.0004406859,0.00003044623,0.6905776,0.00001762313,0.000001700366,0.000003202931,0.000184302,0.2962269,0.01037126,0.0006758544,0.001368497,0.0001019949],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.337061,0.00007279466,0.6357368,0.001411658,0.00003948755,0.0001805876,2.408978e-7,0.00006078118,0.02543663],"genre_scores_gemma":[0.9929918,0.00004702338,0.006443475,0.00003034108,0.0000082792,0.00000806788,0.000001844303,0.000003152269,0.0004659831],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6822823,"threshold_uncertainty_score":0.1899211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02558771438721698,"score_gpt":0.280573750903116,"score_spread":0.254986036515899,"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."}}