{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001382428,0.00145036,0.001146996,0.0008083897,0.0005098957,0.001267794,0.00290652,0.001332308,0.002260032],"category_scores_gemma":[0.004509275,0.0006507811,0.0009007436,0.000796558,0.001447545,0.004885665,0.002727932,0.002789679,0.001244999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007595453,"about_ca_system_score_gemma":0.001112295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00469138,"about_ca_topic_score_gemma":0.008458031,"domain_scores_codex":[0.9993136,0.0001193086,0.00003596982,0.0003237917,0.0001085616,0.00009877906],"domain_scores_gemma":[0.9981477,0.0005629504,0.0001594938,0.0007350678,0.0002486085,0.0001462487],"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":[0.0007721693,0.0006918958,0.005779948,0.0002998411,0.0002094167,0.0001929257,0.0008811603,0.1838629,0.07542989,0.009392211,0.006349984,0.7161376],"study_design_scores_gemma":[0.000027017,0.0002636483,0.001467424,0.00003205657,0.00005785115,0.0001217602,0.0001033821,0.9485639,0.02793209,0.01848921,0.002897703,0.00004395228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1865046,0.001016596,0.7981532,0.0006325669,0.0001641613,0.0001404419,0.0003480475,0.008481812,0.004558499],"genre_scores_gemma":[0.816378,0.0003451489,0.1760566,0.0003665719,0.0000787969,0.0001055783,0.001195582,0.0005588973,0.004914782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00469138,"threshold_uncertainty_score":0.009328187,"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."}}