{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001247547,0.0001795715,0.0002953196,0.0004360556,0.0001364209,0.0004696119,0.0005969458,0.00003094118,0.00004804211],"category_scores_gemma":[0.00007797187,0.0001417785,0.0001643411,0.0005420214,0.00005969093,0.001232946,0.00009151573,0.0006623236,0.0000262576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009586439,"about_ca_system_score_gemma":0.0003621371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003742863,"about_ca_topic_score_gemma":0.000001312301,"domain_scores_codex":[0.9980497,0.0001818028,0.0005578993,0.0002433498,0.0006502952,0.0003169495],"domain_scores_gemma":[0.9988527,0.0002073264,0.0003439864,0.0001989278,0.0002391963,0.0001578832],"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":[0.0003884227,0.0005247786,0.03103503,0.001055193,0.001547561,0.00825878,0.197348,0.1104738,0.06923259,0.04792801,0.006621881,0.5255859],"study_design_scores_gemma":[0.001340155,0.0003293939,0.001417112,0.0007639916,0.00006349356,0.0008616943,0.004500027,0.940143,0.0005657663,0.00137534,0.04824731,0.0003927111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01917796,0.0008338997,0.9692425,0.003087006,0.0008714813,0.00007454584,2.996473e-7,0.0001964069,0.006515914],"genre_scores_gemma":[0.6817116,0.00003145165,0.3175784,0.0002389658,0.0001383958,0.000001149034,4.738912e-7,0.0000251487,0.0002744585],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8296692,"threshold_uncertainty_score":0.5781559,"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."}}