{"id":"W4391916407","doi":"","title":"Adaptation de domaine par une méthode d'apprentissage profond parcimonieuse. Application à la segmentation d'images biomédicales.","year":2023,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"French Infrastructure for Integrated Structural Biology; Centre National de la Recherche Scientifique; Université de Strasbourg; Institute of Genetics; Institut National de la Santé et de la Recherche Médicale; Agence Nationale de la Recherche","keywords":"Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01678242,0.0004745129,0.0004927969,0.0004182272,0.002085658,0.0002235215,0.0009267904,0.0008411193,0.0004745623],"category_scores_gemma":[0.004158944,0.0005584133,0.0002015277,0.002610035,0.0009335002,0.0004823492,0.0005267755,0.001251457,0.001365869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005752061,"about_ca_system_score_gemma":0.0009685943,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01005528,"about_ca_topic_score_gemma":0.01329063,"domain_scores_codex":[0.9699994,0.02541196,0.001494215,0.001072919,0.0007769723,0.001244523],"domain_scores_gemma":[0.9863843,0.008196481,0.001001336,0.001714118,0.002129502,0.0005742947],"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":[0.00008401743,0.001144907,0.03022697,0.001874842,0.0001122824,0.00003630409,0.09877232,0.0006059199,0.03948236,0.1393553,0.0177815,0.6705233],"study_design_scores_gemma":[0.001863169,0.00000858451,0.05250955,0.00879536,0.0003204697,0.00004210959,0.03958551,0.4846588,0.2105099,0.07021266,0.1297285,0.001765469],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1740687,0.002650594,0.7037793,0.1029519,0.0008002242,0.002798922,0.0003292329,0.000926924,0.01169413],"genre_scores_gemma":[0.8762857,0.005599824,0.08534389,0.0003501464,0.0001877566,0.001089457,0.001837482,0.0001661374,0.02913966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7022169,"threshold_uncertainty_score":0.9996867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06812015622039959,"score_gpt":0.3655989163978228,"score_spread":0.2974787601774232,"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."}}