{"id":"W2969211464","doi":"10.1109/iccv.2019.00040","title":"Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Kwanjeong Educational Foundation; National Science Foundation","keywords":"Forgetting; Leverage (statistics); Overfitting; Computer science; Artificial intelligence; Machine learning; Code (set theory); Labeled data; Distillation; Artificial neural network; Task (project management); Generalization; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.003849429,0.001928053,0.002209492,0.001188139,0.0009215952,0.001227967,0.003906534,0.001798062,0.001265242],"category_scores_gemma":[0.0169654,0.0008711723,0.0009577478,0.001138518,0.001667702,0.004686224,0.003156166,0.003572601,0.0009017908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008548835,"about_ca_system_score_gemma":0.001698248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004549069,"about_ca_topic_score_gemma":0.008915912,"domain_scores_codex":[0.9981797,0.0004353724,0.0001265688,0.0006174046,0.0004765873,0.00016438],"domain_scores_gemma":[0.9885206,0.004830069,0.0007560576,0.00420983,0.00122001,0.000463536],"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":[0.0009764149,0.000715943,0.01564302,0.0006467815,0.0003295048,0.0009681676,0.000707343,0.2904651,0.02797708,0.009020937,0.02033524,0.6322145],"study_design_scores_gemma":[0.00004314849,0.0001497844,0.001201512,0.00004084048,0.00004504147,0.0003098359,0.00005715799,0.9663464,0.01480816,0.01473964,0.002220071,0.00003839075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1151831,0.001785645,0.8738088,0.0006807098,0.0002796582,0.0001353452,0.0004786143,0.006125626,0.001522388],"genre_scores_gemma":[0.7895901,0.0006715273,0.2012426,0.0008915566,0.0002966718,0.0002059622,0.002493288,0.0004576777,0.004150586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004549069,"threshold_uncertainty_score":0.02035797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04958758441825139,"score_gpt":0.281441131426253,"score_spread":0.2318535470080016,"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."}}