{"id":"W4393774538","doi":"10.5281/zenodo.3902505","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); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005728975,0.003447876,0.002083,0.004972854,0.001611282,0.003250053,0.002578257,0.002296703,0.00748221],"category_scores_gemma":[0.01141649,0.0009037546,0.003658774,0.003524487,0.001353995,0.003095625,0.003436723,0.002194402,0.007923137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002263126,"about_ca_system_score_gemma":0.002313031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008117403,"about_ca_topic_score_gemma":0.0167896,"domain_scores_codex":[0.9943342,0.001151579,0.0004565512,0.001743,0.001804635,0.0005098956],"domain_scores_gemma":[0.9923579,0.002823788,0.0003825123,0.001849305,0.00220359,0.0003829767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003684611,0.001136406,0.02571564,0.003625854,0.001927417,0.0008246175,0.0009531081,0.1649049,0.04822648,0.01043054,0.1496044,0.5889661],"study_design_scores_gemma":[0.000213553,0.0009808431,0.04018531,0.0006250758,0.0006367594,0.001444552,0.001084562,0.8047705,0.06219783,0.03138237,0.05623161,0.0002469462],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.3078972,0.01026652,0.519374,0.001607947,0.0007137446,0.0009855989,0.07263675,0.05609665,0.03042171],"genre_scores_gemma":[0.4173694,0.00230988,0.2036179,0.0009561673,0.0002533206,0.0006648393,0.3468803,0.009704799,0.01824354],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.008117403,"threshold_uncertainty_score":0.03029805,"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."}}