{"id":"W3097943992","doi":"10.1016/j.media.2021.102146","title":"Self-paced and self-consistent co-training for semi-supervised image segmentation","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Segmentation; Robustness (evolution); Cross entropy; Image segmentation; Machine learning; Pattern recognition (psychology); Entropy (arrow of time); Training set; Deep neural networks; Artificial neural network; Deep learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00208256,0.000881591,0.001797628,0.0009104268,0.0005367766,0.0008724765,0.002479147,0.002142422,0.00145568],"category_scores_gemma":[0.005012926,0.0007501263,0.0009404339,0.001059923,0.0009225488,0.001428376,0.001983276,0.001716853,0.0008824213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004728328,"about_ca_system_score_gemma":0.001164729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003413564,"about_ca_topic_score_gemma":0.005407036,"domain_scores_codex":[0.9990259,0.000264759,0.00005552954,0.0003786829,0.0001659375,0.0001092723],"domain_scores_gemma":[0.9970849,0.001606733,0.0002259118,0.0004621604,0.0004809699,0.0001392936],"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":[0.0007826745,0.0004633723,0.001406631,0.0003571704,0.0002460135,0.0001916697,0.0002926801,0.31729,0.05636334,0.003349563,0.006536111,0.6127208],"study_design_scores_gemma":[0.000006029792,0.00002978342,0.0002668149,0.000005939474,0.00001073568,0.00004849389,0.00001015277,0.9931304,0.005061024,0.001089414,0.0003344895,0.000006761765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01843966,0.0004795835,0.9786505,0.00008893715,0.00004659571,0.00005025031,0.00006483329,0.00169706,0.0004826609],"genre_scores_gemma":[0.5046578,0.0003847068,0.4882483,0.0003684708,0.0001244168,0.0002278156,0.000813277,0.0007205895,0.004454725],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003413564,"threshold_uncertainty_score":0.01101375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02099580457286689,"score_gpt":0.2998354642452361,"score_spread":0.2788396596723692,"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."}}