{"id":"W2734950743","doi":"10.1109/ijcnn.2017.7966307","title":"A fast method for saliency detection by back-propagating a convolutional neural network and clamping its partial outputs","year":2017,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Computer science; Pascal (unit); Convolutional neural network; Pixel; Pattern recognition (psychology); Salience (neuroscience); Deep learning; Benchmark (surveying); Gradient descent; Object detection; Image (mathematics); Computer vision; Artificial neural network","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":[0.0006283781,0.001500982,0.000698437,0.001499234,0.0003876653,0.0005610302,0.001445091,0.0007654152,0.002470975],"category_scores_gemma":[0.001488386,0.000589211,0.0007485532,0.0006220049,0.0004926855,0.001307724,0.001023244,0.001079738,0.0007475088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00098853,"about_ca_system_score_gemma":0.00110199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005469031,"about_ca_topic_score_gemma":0.009191948,"domain_scores_codex":[0.9996942,0.00002800329,0.00001349309,0.00009509608,0.0001302015,0.00003896673],"domain_scores_gemma":[0.9995584,0.0001170945,0.00004929595,0.00007311619,0.0001648656,0.00003712894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002182403,0.0001132862,0.001134584,0.0002314871,0.0001546576,0.0001554807,0.0001264493,0.08457325,0.09425736,0.008475714,0.005460926,0.8050985],"study_design_scores_gemma":[0.00002550455,0.00007237397,0.0008039279,0.00001556946,0.00003365824,0.0001392762,0.00001130053,0.9610039,0.029946,0.004798065,0.003129837,0.00002057436],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005685314,0.000211648,0.9919971,0.00005477809,0.00005201051,0.00004658077,0.0000424346,0.001272999,0.0006370815],"genre_scores_gemma":[0.2020853,0.0003677574,0.7921657,0.0001825006,0.0001034989,0.0001196761,0.0003127763,0.0003674465,0.004295334],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005469031,"threshold_uncertainty_score":0.01087439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03988104908559037,"score_gpt":0.3265477079992886,"score_spread":0.2866666589136982,"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."}}