{"id":"W4382318976","doi":"10.1609/aaai.v37i9.26238","title":"MetaZSCIL: A Meta-Learning Approach for Generalized Zero-Shot Class Incremental Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Meta learning (computer science); Forgetting; Computer science; Artificial intelligence; Machine learning; Class (philosophy); Task (project management); Feature (linguistics); Process (computing); Generative grammar; Sample (material); Adaptation (eye); Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002159879,0.0003557947,0.0005709032,0.0003308398,0.0006944012,0.0005490263,0.001974699,0.0001247477,0.00006982535],"category_scores_gemma":[0.001174342,0.0002712979,0.0004496996,0.001558647,0.0002175014,0.0005588844,0.0005708713,0.0006259743,0.0001051135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005968029,"about_ca_system_score_gemma":0.0001029207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003099566,"about_ca_topic_score_gemma":0.000002176066,"domain_scores_codex":[0.9969123,0.0001002255,0.0007437129,0.0007995953,0.0008135651,0.0006305745],"domain_scores_gemma":[0.9980754,0.0002615769,0.0006181957,0.0002662167,0.0006359129,0.0001426913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001072396,0.0001035442,0.00009965796,0.00008449415,0.0002665856,5.786828e-7,0.002927931,0.01609046,0.08356487,0.8717759,0.0003749678,0.0246038],"study_design_scores_gemma":[0.0001108938,0.0002704296,0.00004046284,0.00003818013,0.0001708287,0.00000434876,0.001714082,0.8346093,0.1291898,0.03068843,0.002794545,0.0003687607],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07829308,0.00009865824,0.880305,0.005324129,0.0007516396,0.00200182,0.000008704814,0.001288999,0.03192798],"genre_scores_gemma":[0.9656916,0.000045569,0.03089114,0.0002490339,0.00006919363,0.0002364082,0.000007532257,0.00003434353,0.00277523],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8873985,"threshold_uncertainty_score":0.9999739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.230948496481997,"score_gpt":0.3343297526525874,"score_spread":0.1033812561705904,"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."}}