{"id":"W4224255863","doi":"10.24963/ijcai.2022/177","title":"Continual Semantic Segmentation Leveraging Image-level Labels and Rehearsal","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Forgetting; Computer science; Leverage (statistics); Pascal (unit); Artificial intelligence; Segmentation; Machine learning; Deep learning; Deep neural networks","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":[],"consensus_categories":[],"category_scores_codex":[0.0009098354,0.0002031171,0.0002137298,0.0002439481,0.0005729305,0.0004438072,0.001283309,0.00003825089,0.0002456591],"category_scores_gemma":[0.0003395188,0.0001819999,0.00009576826,0.0003988038,0.0001916619,0.0006403768,0.0009321505,0.0004616553,0.00003454704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001314357,"about_ca_system_score_gemma":0.00007895942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006631703,"about_ca_topic_score_gemma":0.000008487544,"domain_scores_codex":[0.9976324,0.00004520269,0.0005938117,0.0005047684,0.0009583017,0.0002654996],"domain_scores_gemma":[0.998565,0.0001239104,0.0005097185,0.0001689316,0.0005538849,0.00007856194],"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":[0.00008640192,0.0001697249,0.0006169988,0.00003130009,0.00004866362,0.000003263058,0.00718623,0.0006210442,0.0611656,0.8902091,0.0003201028,0.03954157],"study_design_scores_gemma":[0.0003768955,0.000509811,0.006210398,0.0003670714,0.00003448646,0.0001378251,0.01397007,0.5532087,0.2263071,0.19583,0.002228853,0.0008187636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5560878,0.00006082879,0.3612452,0.05250603,0.003754897,0.001267171,0.00005860779,0.0003716729,0.02464786],"genre_scores_gemma":[0.9873959,0.00002484206,0.01124364,0.000591423,0.00006337838,0.00004501703,0.000002947764,0.000013991,0.0006188295],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6943791,"threshold_uncertainty_score":0.742174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08905293292888322,"score_gpt":0.288522880963504,"score_spread":0.1994699480346208,"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."}}