{"id":"W4293069434","doi":"10.5194/isprs-archives-xliii-b3-2022-41-2022","title":"IMPROVING CNN-BASED BUILDING SEMANTIC SEGMENTATION USING OBJECT BOUNDARIES","year":2022,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Computer science; Segmentation; Leverage (statistics); Artificial intelligence; Convolutional neural network; Encoder; Deep learning; Ground truth; Pattern recognition (psychology); Machine learning; Data mining","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.001584518,0.0004235134,0.0003956545,0.00102566,0.004085913,0.001479927,0.00274505,0.00005960513,0.000006913694],"category_scores_gemma":[0.0005042764,0.0002990078,0.0003544083,0.001653219,0.002751505,0.0008454518,0.002062681,0.0005516475,0.000001406066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001332006,"about_ca_system_score_gemma":0.00053953,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6720306,"about_ca_topic_score_gemma":0.07080215,"domain_scores_codex":[0.9947755,0.0004353348,0.001428869,0.000529723,0.002247146,0.0005834786],"domain_scores_gemma":[0.9955851,0.001188199,0.002161301,0.0006510895,0.0002729398,0.0001413459],"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":[0.00007428731,0.00001943958,0.0001368173,0.00003133768,0.00004972729,3.678311e-7,0.002409578,0.04771879,0.00866708,0.00003966987,0.0000206615,0.9408323],"study_design_scores_gemma":[0.0006577445,0.0001344041,0.0006886018,0.0001457853,0.000038007,0.0001565636,0.001351491,0.973315,0.01195433,0.008715827,0.002511212,0.0003310388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01265423,0.00003397497,0.9787302,0.00401626,0.002200942,0.000809474,0.00007259365,0.00008347668,0.001398825],"genre_scores_gemma":[0.9702949,0.00003187659,0.02796396,0.001519355,0.0001088133,0.000001187526,0.00002896866,0.0000129233,0.0000380329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9576406,"threshold_uncertainty_score":0.9999624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01861091933652285,"score_gpt":0.2675086403763602,"score_spread":0.2488977210398374,"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."}}