{"id":"W2974547027","doi":"10.26685/urncst.154","title":"Image Classification by Image Subsets for Fine-Grained Image Recognition","year":2019,"lang":"en","type":"article","venue":"Undergraduate Research in Natural and Clinical Science and Technology (URNCST) Journal","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"University of Windsor","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Pooling; Salience (neuroscience); Salient; Feature extraction; Image (mathematics); Image processing; Context (archaeology); Feature (linguistics); Contextual image classification; Convolutional neural network; Convolution (computer science); Process (computing); Cognitive neuroscience of visual object recognition; Computer vision; Artificial neural network; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.008419525,0.0002094058,0.0003630121,0.00124088,0.000799626,0.0007336132,0.001288403,0.0002677226,0.000007398256],"category_scores_gemma":[0.003319565,0.0001565598,0.00008080735,0.003646781,0.002651918,0.002797371,0.0006417299,0.00203491,0.00004181107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001680808,"about_ca_system_score_gemma":0.0003226382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007704302,"about_ca_topic_score_gemma":0.000008416236,"domain_scores_codex":[0.9962648,0.000220326,0.0007057412,0.0009178145,0.0008383558,0.001052976],"domain_scores_gemma":[0.9965148,0.0009610333,0.0002477043,0.0004135889,0.001570703,0.0002921922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001267739,0.0002510087,0.002538761,0.00005045811,0.00001794469,0.00005668768,0.00002844867,1.989999e-8,0.2615275,0.01179589,0.00603123,0.7175753],"study_design_scores_gemma":[0.002784739,0.00188126,0.002502029,0.00023281,0.00001064881,0.0004490171,0.0003306188,0.01855572,0.04440547,0.9232913,0.005014757,0.0005416627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6240098,0.002739419,0.1693642,0.1987976,0.0007854442,0.002336812,0.00002896011,0.0004815427,0.001456227],"genre_scores_gemma":[0.9091408,0.005596726,0.08459067,0.0001928873,0.00008400087,0.00003391882,0.000007620867,0.0000140914,0.0003392641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9114954,"threshold_uncertainty_score":0.9771103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06708108773728082,"score_gpt":0.4281316505041172,"score_spread":0.3610505627668363,"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."}}