{"id":"W2501524975","doi":"10.1007/978-3-319-41501-7_41","title":"Object Detection and Localization Using Deep Convolutional Networks with Softmax Activation and Multi-class Log Loss","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Softmax function; Computer science; Artificial intelligence; Minimum bounding box; Convolutional neural network; Pattern recognition (psychology); Region of interest; Computer vision; Deep learning; Object detection; Object (grammar); Contextual image classification; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007028426,0.001703026,0.00129781,0.001230011,0.0005493933,0.001726943,0.002469107,0.001683853,0.007187106],"category_scores_gemma":[0.001168708,0.0009366357,0.0010804,0.001250122,0.0004841591,0.001770996,0.002106878,0.001642021,0.007084725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001129195,"about_ca_system_score_gemma":0.001438162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00914452,"about_ca_topic_score_gemma":0.01750863,"domain_scores_codex":[0.999514,0.00002790103,0.00001871694,0.0002099302,0.0001312246,0.00009832439],"domain_scores_gemma":[0.9995447,0.000108295,0.00004510966,0.0001154858,0.0001458241,0.0000405403],"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":[0.0002799951,0.0001489463,0.0008045398,0.0001389299,0.00008035663,0.0001173755,0.00003793578,0.03050102,0.0414505,0.003825159,0.0110784,0.9115367],"study_design_scores_gemma":[0.00001632332,0.00008192995,0.001179065,0.00003626512,0.00005303899,0.0001926725,0.00002518293,0.9266615,0.0576755,0.007849169,0.006195141,0.0000342181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0107773,0.0007218004,0.9777493,0.0002336855,0.0001393306,0.00005053973,0.0003801256,0.006926856,0.003021115],"genre_scores_gemma":[0.2645908,0.00110137,0.6949298,0.0003920254,0.0001356406,0.0001298535,0.002516612,0.0005692945,0.03563455],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00914452,"threshold_uncertainty_score":0.02404326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01630436585931179,"score_gpt":0.2411829195110352,"score_spread":0.2248785536517234,"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."}}