{"id":"W4399708787","doi":"10.1016/j.media.2024.103239","title":"CCSI: Continual Class-Specific Impression for data-free class incremental learning","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vancouver General Hospital; Vector Institute; University of British Columbia","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Forgetting; Machine learning; Class (philosophy); Margin (machine learning); Cross entropy; Normalization (sociology); Deep learning; Pattern recognition (psychology); Data mining","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002105115,0.0001924547,0.0003671272,0.0004275603,0.000265253,0.0008443314,0.002196477,0.000131836,0.001127845],"category_scores_gemma":[0.001299301,0.0001612701,0.0002770562,0.001494029,0.0001355852,0.001015362,0.001234334,0.0005657184,0.0001738803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006053825,"about_ca_system_score_gemma":0.0001169225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004395029,"about_ca_topic_score_gemma":0.00004339937,"domain_scores_codex":[0.9968029,0.0002401537,0.0004951016,0.0008898859,0.001152371,0.0004196433],"domain_scores_gemma":[0.9976529,0.0007470868,0.0001039518,0.001070293,0.0001059657,0.0003197392],"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":[0.0000412638,0.0001700045,0.0008891753,0.00008825539,0.001603885,0.0004362375,0.001632426,0.0002484686,0.00704067,0.01267824,0.2000222,0.7751492],"study_design_scores_gemma":[0.0003844965,0.00003446605,0.000190841,0.00003149389,0.0001609211,0.000005330133,0.0001827551,0.6721749,0.0001399061,0.0001591477,0.3263901,0.000145653],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001669267,0.0009197443,0.9889981,0.004590357,0.0004103236,0.000124417,0.00002009814,0.0003914797,0.002876284],"genre_scores_gemma":[0.8630407,0.0003297949,0.1260751,0.001599591,0.000904258,0.00006189327,0.001156641,0.00005807495,0.006773996],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8629229,"threshold_uncertainty_score":0.9997852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03183739835390364,"score_gpt":0.3246820824993474,"score_spread":0.2928446841454437,"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."}}