{"id":"W3089098255","doi":"10.1109/access.2020.3026684","title":"Semantic Segmentation Using a GAN and a Weakly Supervised Method Based on Deep Transfer Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Upsampling; Artificial intelligence; Computer science; Segmentation; Transfer of learning; Generalization; Pattern recognition (psychology); Deep learning; Bilinear interpolation; Deconvolution; Image segmentation; Pooling; Computer vision; Image (mathematics); Algorithm; 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":[0.0006425263,0.001072424,0.0007949902,0.0006082211,0.000325704,0.0005487176,0.001264563,0.0009426289,0.001504704],"category_scores_gemma":[0.001127831,0.0004067654,0.001026102,0.0005140434,0.0008771757,0.001338881,0.001079749,0.001502067,0.0004913248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008116563,"about_ca_system_score_gemma":0.0007687858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002451667,"about_ca_topic_score_gemma":0.00343284,"domain_scores_codex":[0.999619,0.00009360391,0.00001594442,0.0001474849,0.00007805147,0.00004587508],"domain_scores_gemma":[0.9997122,0.00008498057,0.00003712247,0.00008392191,0.00005513179,0.00002662401],"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":[0.0001951578,0.0001535194,0.001077007,0.00009110118,0.0001033616,0.0001719738,0.0001462472,0.6836608,0.03567701,0.02189351,0.002870193,0.2539601],"study_design_scores_gemma":[0.000002391901,0.00001863412,0.0000773217,0.000002442019,0.000004443853,0.00002261614,0.000003992061,0.9935807,0.002392532,0.003560584,0.0003300316,0.000004361784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01122118,0.00009231506,0.9863911,0.00009856405,0.00002794369,0.00003604984,0.00003938858,0.0008692206,0.0012243],"genre_scores_gemma":[0.6334651,0.000235908,0.3595503,0.0003084842,0.0000800241,0.0001691929,0.0005173926,0.0002928819,0.005380846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002451667,"threshold_uncertainty_score":0.005888999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06924967432766485,"score_gpt":0.3315849147437667,"score_spread":0.2623352404161018,"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."}}