{"id":"W4393666338","doi":"10.5281/zenodo.3902506","title":"A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Image (mathematics); Pattern recognition (psychology); Semantic analysis (machine learning); Natural language processing","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002624115,0.0002387507,0.0004825526,0.001025187,0.0004150214,0.0006099214,0.00204452,0.0001120078,0.001486705],"category_scores_gemma":[0.0001946925,0.0002306442,0.0001614952,0.002794255,0.0001379966,0.0002953235,0.001637307,0.0003572167,0.001092328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001786149,"about_ca_system_score_gemma":0.000007356248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004325376,"about_ca_topic_score_gemma":0.000001069515,"domain_scores_codex":[0.9974514,0.0005430885,0.0005290424,0.0006189148,0.0005894193,0.0002681768],"domain_scores_gemma":[0.9981028,0.00005216339,0.000321791,0.0008393723,0.0005559571,0.0001278838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002882253,0.0002309821,9.040624e-7,0.0002800036,0.0002673165,0.00002326722,0.0004396656,0.000006846562,0.01495642,0.000300591,0.9724331,0.01103202],"study_design_scores_gemma":[0.0003759331,0.0002090283,0.0009200547,0.00005789902,0.0001883283,0.000008769346,0.0001343636,0.006292065,0.003282426,0.00007939997,0.9881696,0.0002821546],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0004860319,0.00006975871,0.2059345,0.0009567522,0.00008875654,0.001002548,0.7900159,0.0006897299,0.0007560409],"genre_scores_gemma":[0.00484194,0.0004054323,0.001538155,0.000156635,0.00004167884,1.937098e-7,0.9927072,0.0002767889,0.00003195938],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2043964,"threshold_uncertainty_score":0.9996855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03536876243167774,"score_gpt":0.2713171068730429,"score_spread":0.2359483444413652,"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."}}