{"id":"W3025800305","doi":"10.1016/j.patcog.2020.107404","title":"U2-Net: Going deeper with nested U-structure for salient object detection","year":2020,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2295,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Pooling; Architecture; Net (polyhedron); Salient; Artificial intelligence; Code (set theory); Residual; Network architecture; Scratch; Object detection; Computer architecture; Pattern recognition (psychology); Parallel computing; Algorithm; Computer network; Programming language; 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":[0.000695895,0.001177356,0.001312723,0.001193772,0.0008668652,0.001510352,0.002744171,0.001546479,0.01325119],"category_scores_gemma":[0.00318877,0.0008020927,0.001170166,0.0009385457,0.000826262,0.004394261,0.002933183,0.001229411,0.003327994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009474796,"about_ca_system_score_gemma":0.001214647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007221139,"about_ca_topic_score_gemma":0.0124226,"domain_scores_codex":[0.9996382,0.00004509135,0.000024175,0.000158524,0.00007042386,0.00006353994],"domain_scores_gemma":[0.9990947,0.0003331564,0.00005483051,0.0002646503,0.000144319,0.0001083126],"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":[0.001513477,0.0004499859,0.002470315,0.0004950861,0.0001410356,0.0003530263,0.0003753371,0.03876025,0.04096118,0.05743808,0.03413902,0.8229032],"study_design_scores_gemma":[0.00006342628,0.0002028064,0.0004500105,0.0000531404,0.00005481774,0.0001127835,0.00007365266,0.865433,0.02709873,0.09679061,0.009632162,0.00003490827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02935196,0.0004878686,0.9455507,0.0002614753,0.0002199081,0.000130081,0.0007534583,0.01839011,0.004854473],"genre_scores_gemma":[0.2774099,0.000241468,0.7107743,0.0005435377,0.0001166876,0.00018839,0.001696896,0.001697207,0.007331509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01325119,"threshold_uncertainty_score":0.04432964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02983440205488718,"score_gpt":0.2409729606479623,"score_spread":0.2111385585930751,"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."}}