{"id":"W3005428380","doi":"","title":"Selective Segmentation Networks Using Top-Down Attention","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Segmentation; Top-down and bottom-up design; Task (project management); Baseline (sea); Artificial intelligence; Benchmark (surveying); Selection (genetic algorithm); Hierarchy; Machine learning; Convolutional neural network; Feed forward; Feature selection; Object (grammar); Pattern recognition (psychology)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007927663,0.0002755846,0.0002427693,0.0001264613,0.0002554726,0.0001080888,0.001050205,0.0002014846,0.000007188418],"category_scores_gemma":[0.00001117708,0.0003540253,0.0001576957,0.001151363,0.00005944479,0.0005245756,0.001374913,0.0006063311,0.00003693736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003970636,"about_ca_system_score_gemma":0.00009738805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003850413,"about_ca_topic_score_gemma":0.0000115171,"domain_scores_codex":[0.9980826,0.0001257847,0.0002011989,0.001191843,0.0000875211,0.0003110479],"domain_scores_gemma":[0.9985381,0.00007427756,0.0003486495,0.0007331256,0.0001536778,0.0001522158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001160189,0.00002858479,0.001091735,0.00001597595,0.00004376605,0.00003050317,0.00006493543,0.95431,0.0006548695,0.04261479,0.0001532294,0.0009800034],"study_design_scores_gemma":[0.0002149076,0.00002486195,0.001220224,0.00003499536,0.00005275218,0.000003491064,0.00002434312,0.9611585,0.0002318045,0.03664087,0.00006780556,0.0003254647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07157861,0.00003514612,0.9266064,0.0001742818,0.0003667049,0.000508826,0.000005214973,0.0003496628,0.0003751407],"genre_scores_gemma":[0.9785991,0.00009721141,0.02071186,0.000180155,0.0001815871,0.000003280202,0.00004267717,0.00002034907,0.0001637497],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9070205,"threshold_uncertainty_score":0.9998912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08128177256051665,"score_gpt":0.2212799858855515,"score_spread":0.1399982133250349,"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."}}