{"id":"W3186163092","doi":"10.48550/arxiv.2107.13741","title":"Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Pattern recognition (psychology); Task (project management); Semi-supervised learning; Supervised learning; Encoder; Machine learning; Process (computing); Training set; Labeled data; Medical imaging; Image (mathematics); Noise (video); Set (abstract data type); Exploit; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006478513,0.000399059,0.0006100569,0.000208906,0.000320419,0.0003631519,0.0009607156,0.0002967189,0.0001998337],"category_scores_gemma":[0.00020647,0.0003953927,0.0003248235,0.0005688954,0.0001036883,0.0006920269,0.0006844793,0.0008621166,0.00002224676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002045466,"about_ca_system_score_gemma":0.0006444267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003738535,"about_ca_topic_score_gemma":0.00003794408,"domain_scores_codex":[0.997286,0.0004656286,0.0002693825,0.00123803,0.0003129105,0.0004280026],"domain_scores_gemma":[0.9977627,0.0005284914,0.0003596372,0.0005238035,0.000509039,0.0003162863],"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":[0.000678808,0.001132061,0.003391026,0.001334408,0.01472804,0.003641553,0.01917194,0.8304142,0.002788536,0.1136301,0.0005202566,0.008569044],"study_design_scores_gemma":[0.002379858,0.0001566365,0.0002266451,0.00009281054,0.0008600086,0.00001340841,0.001648669,0.9921888,0.0006141167,0.0006359258,0.0006326593,0.0005505215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0463936,0.00009858882,0.9506564,0.0002963248,0.0002202995,0.0006182569,0.000005826515,0.0004394676,0.001271312],"genre_scores_gemma":[0.915273,0.0001338285,0.08270882,0.0002953958,0.00005801035,0.0000150611,0.0001038175,0.0000357721,0.001376279],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8688794,"threshold_uncertainty_score":0.9998498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06673264261701548,"score_gpt":0.2105615330116287,"score_spread":0.1438288903946132,"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."}}