{"id":"W4387951161","doi":"10.1109/ccece58730.2023.10288934","title":"Scene Parsing Using Fully Convolutional Network for Semantic Segmentation","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Artificial intelligence; Parsing; Segmentation; Convolutional neural network; Transfer of learning; Robustness (evolution); Inference; Deep learning; Image segmentation; Object detection; Pattern recognition (psychology); Computer vision; Natural language processing; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0001548415,0.00008153979,0.00008248669,0.00005108852,0.0003490024,0.00005955685,0.0002424014,0.00002672167,0.000005731463],"category_scores_gemma":[0.00001152352,0.0000832951,0.000040895,0.000854529,0.0000251088,0.0003216044,0.0001015457,0.00004093273,0.00005081253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005442027,"about_ca_system_score_gemma":0.00003828532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004213833,"about_ca_topic_score_gemma":0.000006292804,"domain_scores_codex":[0.9990751,0.00001886736,0.0001704515,0.0002803916,0.0001395502,0.0003156266],"domain_scores_gemma":[0.9994037,0.0001904248,0.00006564018,0.0002213172,0.00006725905,0.00005172416],"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":[0.000008139572,0.00002380179,0.000951737,0.00001917658,0.00001863984,0.000002304547,0.00007768441,0.6671168,0.01572838,0.2741739,0.01153812,0.03034132],"study_design_scores_gemma":[0.0001727359,0.00001413579,0.001050613,0.00001132246,0.000004725601,0.000006801381,0.000009906928,0.9603148,0.0008796053,0.03624731,0.001184795,0.0001033295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01151084,0.0000319479,0.9862992,0.0009607666,0.0002893313,0.0003720244,0.00000224008,0.0004244209,0.0001092188],"genre_scores_gemma":[0.181883,0.0000106464,0.8168452,0.0004861192,0.0003157338,0.00007593978,0.0000343247,0.00001229166,0.0003368131],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.293198,"threshold_uncertainty_score":0.3396676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06237313761655348,"score_gpt":0.3260679198329695,"score_spread":0.263694782216416,"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."}}