{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003712879,0.001254196,0.0005974367,0.0005273857,0.0003982396,0.0008193026,0.001467812,0.001141937,0.003297678],"category_scores_gemma":[0.0008508535,0.0005482467,0.0007713241,0.0005692456,0.000644277,0.001603804,0.00119263,0.001217083,0.0009890383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014214,"about_ca_system_score_gemma":0.0008888957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00724853,"about_ca_topic_score_gemma":0.01429191,"domain_scores_codex":[0.9997569,0.00002959969,0.000008414055,0.0001091251,0.00004226048,0.00005357399],"domain_scores_gemma":[0.9997825,0.00007205435,0.00002577506,0.00004986044,0.00004655409,0.0000232833],"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":[0.0003760654,0.0002067212,0.001195854,0.0001398676,0.0002029442,0.0002134991,0.0001407207,0.5441411,0.05996856,0.01881819,0.009781508,0.3648149],"study_design_scores_gemma":[0.000009971301,0.00005284677,0.0003260902,0.000006679206,0.00002648031,0.0000272792,0.000008705771,0.9795807,0.008221262,0.01058735,0.00114454,0.000008012945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07449017,0.000847646,0.90932,0.0003958116,0.0001305226,0.00008039793,0.0003727292,0.005267018,0.009095679],"genre_scores_gemma":[0.8257257,0.0004936001,0.1564112,0.0004368033,0.0001165787,0.0001275054,0.001154858,0.0003433836,0.01519051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00724853,"threshold_uncertainty_score":0.01441264,"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."}}