{"id":"W4390906408","doi":"10.3390/jimaging10010023","title":"Fully Self-Supervised Out-of-Domain Few-Shot Learning with Masked Autoencoders","year":2024,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoencoder; Computer science; Artificial intelligence; Machine learning; Supervised learning; One shot; Domain (mathematical analysis); Shot (pellet); Transformer; Pattern recognition (psychology); Training set; Semi-supervised learning; Deep learning; Artificial neural network; Mathematics","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":[0.001238745,0.001117921,0.001254693,0.0006093642,0.0003550453,0.0005810462,0.001672648,0.001111102,0.001117102],"category_scores_gemma":[0.00313811,0.0005350551,0.0008523997,0.0004533451,0.0007382938,0.001611555,0.001127274,0.001619324,0.0007568075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004767076,"about_ca_system_score_gemma":0.000872385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003036749,"about_ca_topic_score_gemma":0.006587984,"domain_scores_codex":[0.9995078,0.0001101461,0.00002503972,0.0001979401,0.00009888611,0.00006023811],"domain_scores_gemma":[0.9987189,0.0005383895,0.0001147306,0.0003003418,0.0002543626,0.00007330973],"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":[0.0005582176,0.0007161109,0.004474971,0.0002759452,0.0003389057,0.000233736,0.0002770559,0.3326637,0.05169423,0.00354715,0.006558544,0.5986614],"study_design_scores_gemma":[0.00000868137,0.00006402464,0.0005125871,0.000007900083,0.00001407206,0.00006125253,0.00001559426,0.9896021,0.007663767,0.001638611,0.000401325,0.00001005653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07912863,0.0005877109,0.9155943,0.0001452282,0.00009802807,0.0001130243,0.0001777061,0.002727439,0.00142803],"genre_scores_gemma":[0.7161546,0.0002608973,0.276707,0.000397927,0.00009185709,0.0001378604,0.001437893,0.0002140313,0.004597818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003036749,"threshold_uncertainty_score":0.006551206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01413602564620975,"score_gpt":0.2531754631964844,"score_spread":0.2390394375502746,"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."}}