{"id":"W2798322161","doi":"10.1016/j.imavis.2020.103887","title":"EML-NET: An Expandable Multi-Layer NETwork for saliency prediction","year":2020,"lang":"en","type":"preprint","venue":"Image and Vision Computing","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Leverage (statistics); Encoder; Inference; Scalability; Artificial intelligence; Encoding (memory); Layer (electronics); Computational model; Machine learning; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000689777,0.000319408,0.0003664877,0.000113018,0.0006143544,0.0009085814,0.000568371,0.0002302258,0.000007047675],"category_scores_gemma":[0.00006539603,0.0003108176,0.0001601412,0.0002512027,0.00004120408,0.0006312304,0.001164028,0.000440657,0.00001369611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003753014,"about_ca_system_score_gemma":0.0000623409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003886453,"about_ca_topic_score_gemma":0.000006409893,"domain_scores_codex":[0.9974333,0.0001576632,0.0005517188,0.001146823,0.0002944707,0.0004160407],"domain_scores_gemma":[0.9986767,0.00008591458,0.0003066378,0.0004931924,0.0002161107,0.0002215096],"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":[0.0001181749,0.0005661366,0.002269248,0.0009694002,0.0001197792,0.00003299695,0.005107011,0.02864009,0.02011608,0.003010347,0.01436194,0.9246888],"study_design_scores_gemma":[0.0006332181,0.0004195746,0.006454153,0.0002071012,0.00001941719,0.00001140172,0.00005042341,0.9867601,0.0004328851,0.003066198,0.001622549,0.0003229881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03613212,0.0002234115,0.9595722,0.0003531527,0.002385643,0.0006066028,0.00001765907,0.0005889114,0.0001202846],"genre_scores_gemma":[0.6964945,0.00004946566,0.3015577,0.0005127925,0.001147532,0.00002734821,0.00008207287,0.00003426012,0.00009427584],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.95812,"threshold_uncertainty_score":0.9999344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05634051383164976,"score_gpt":0.3734769481801531,"score_spread":0.3171364343485034,"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."}}