{"id":"W4392903502","doi":"10.1109/icassp48485.2024.10448032","title":"Unsupervised Continual Learning of Image Representation Via Rememory-Based Simsiam","year":2024,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Henan Institute of Science and Technology; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Computer science; Forgetting; Dependency (UML); Representation (politics); Focus (optics); Process (computing); Artificial intelligence; Image (mathematics); Feature learning; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.000454619,0.0001054857,0.0001424264,0.0001880679,0.0000753885,0.000223875,0.0003051774,0.00004406497,0.0002952167],"category_scores_gemma":[0.0001399528,0.00009796716,0.00009377625,0.0006169935,0.00005085579,0.0005454542,0.00006849896,0.0001920937,0.0001662535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002144421,"about_ca_system_score_gemma":0.00007935953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003790869,"about_ca_topic_score_gemma":0.000003019442,"domain_scores_codex":[0.9986941,0.000154986,0.0002898032,0.0003545457,0.0003263081,0.0001802153],"domain_scores_gemma":[0.9991994,0.0002770722,0.00006452038,0.0002752479,0.0001180508,0.00006574518],"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":[0.00005807613,0.0001458231,0.002274507,0.0002657223,0.00009422976,0.0001779109,0.008020712,0.02276495,0.3997681,0.1101043,0.00376333,0.4525624],"study_design_scores_gemma":[0.0003572836,0.00007299694,0.001150238,0.00003894974,0.000006379946,0.000004542583,0.0002848795,0.967179,0.02322645,0.000502722,0.007043742,0.0001328114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01108196,0.00007988323,0.9652133,0.000813066,0.0002529777,0.0001113582,4.037632e-7,0.0005245232,0.02192252],"genre_scores_gemma":[0.9079995,0.000003276193,0.08866256,0.0001938232,0.00004029638,0.000006041458,0.000009000933,0.00001265093,0.00307284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9444141,"threshold_uncertainty_score":0.3994985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01720036284355687,"score_gpt":0.2806896362105125,"score_spread":0.2634892733669557,"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."}}