{"id":"W3113078706","doi":"10.1007/s11263-022-01706-5","title":"Robots Understanding Contextual Information in Human-Centered Environments Using Weakly Supervised Mask Data Distillation","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Vector Institute; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; AGE-WELL; Nvidia","keywords":"Computer science; Artificial intelligence; Segmentation; Convolutional neural network; Pattern recognition (psychology); Robot; Heuristic; Categorization; Object (grammar); Image segmentation; Machine learning; Computer vision","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":[0.0004312639,0.0001210876,0.0001599152,0.0004157035,0.0001846407,0.000197977,0.002113602,0.00002646758,0.00002317055],"category_scores_gemma":[0.00001205128,0.0001268403,0.00005465732,0.0002357937,0.0000274427,0.003395634,0.001617862,0.000271494,0.00000355975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007655721,"about_ca_system_score_gemma":0.0000458698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008074806,"about_ca_topic_score_gemma":0.000002337663,"domain_scores_codex":[0.9978645,0.0001277746,0.0007364295,0.0002091258,0.0009072948,0.0001548188],"domain_scores_gemma":[0.9987854,0.000102301,0.0006117976,0.0003714532,0.00006776697,0.00006125043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001111741,0.0002278173,0.001166219,0.000003820464,0.00005592332,0.00006186309,0.0007752984,0.9447439,0.005994893,0.01202667,0.0006764272,0.03415594],"study_design_scores_gemma":[0.001212221,0.0001468046,0.002847933,0.0000506347,0.000004922885,0.0002042397,0.00008077459,0.9881522,0.00008031441,0.003631694,0.003456987,0.0001312837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06110801,0.00002805743,0.9368777,0.0007863577,0.0009994445,0.0001360775,0.0000187288,0.00001343341,0.00003223962],"genre_scores_gemma":[0.9607858,0.00001392857,0.03863344,0.0002845198,0.0001734878,0.000001929923,0.00009507473,0.000007301043,0.000004516188],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8996778,"threshold_uncertainty_score":0.5172397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09627518311913438,"score_gpt":0.3382836249925456,"score_spread":0.2420084418734112,"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."}}