{"id":"W4400524898","doi":"10.1109/access.2024.3426542","title":"Memory-Efficient Continual Learning Object Segmentation for Long Videos","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Alliance de recherche numérique du Canada; Microsoft","keywords":"Computer science; Artificial intelligence; Segmentation; Robustness (evolution); Object (grammar); Machine learning; Computer vision; Representation (politics); Market segmentation; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009748195,0.001165444,0.001170209,0.0008307964,0.0004844423,0.0007728474,0.002581486,0.001120968,0.00157787],"category_scores_gemma":[0.002594146,0.0005365849,0.0007613277,0.0007876513,0.0009516861,0.001676179,0.001439697,0.001289067,0.0006872519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008485064,"about_ca_system_score_gemma":0.001284453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008245529,"about_ca_topic_score_gemma":0.008508639,"domain_scores_codex":[0.9995135,0.00005731123,0.00003043402,0.0002297919,0.0001086376,0.00006033562],"domain_scores_gemma":[0.9990894,0.0003198677,0.0001302613,0.0002192326,0.0001712039,0.00007005591],"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":[0.0005747321,0.0002804185,0.00205926,0.0001621525,0.00008496096,0.0001882487,0.0001961195,0.3559153,0.02413114,0.003039951,0.003609489,0.6097582],"study_design_scores_gemma":[0.000007101936,0.00004179074,0.0002343599,0.000005988054,0.000006656297,0.00003513302,0.00001425901,0.994328,0.003506474,0.001395031,0.0004183313,0.000006933993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09279156,0.001149231,0.8985998,0.0002879481,0.00008571538,0.0001028222,0.0002160197,0.004915184,0.001851705],"genre_scores_gemma":[0.7498478,0.0004856485,0.2431356,0.0003466754,0.0001171975,0.0001514134,0.001172573,0.0003547012,0.004388358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008245529,"threshold_uncertainty_score":0.01639509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0325712815419496,"score_gpt":0.3366863776912251,"score_spread":0.3041150961492755,"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."}}