{"id":"W3080805846","doi":"10.5194/isprs-archives-xliii-b3-2020-1507-2020","title":"EVALUATION OF UNet AND UNet++ ARCHITECTURES IN HIGH RESOLUTION IMAGE CHANGE DETECTION APPLICATIONS","year":2020,"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":"Remote-Sensing Image Classification","field":"Engineering","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Computer science; Change detection; Artificial intelligence; Segmentation; Deep learning; Convolutional neural network; Cross entropy; Dice; Task (project management); Hinge loss; Machine learning; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001718831,0.001215999,0.0005431214,0.0006150063,0.0003217977,0.000670972,0.001278299,0.001152212,0.002249199],"category_scores_gemma":[0.004324538,0.000330709,0.0005115619,0.0004890822,0.0004175036,0.001197379,0.0008129443,0.001012713,0.0006630234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009115444,"about_ca_system_score_gemma":0.0007993642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01067278,"about_ca_topic_score_gemma":0.01463135,"domain_scores_codex":[0.999492,0.0001108803,0.00003923054,0.0001389251,0.0001317908,0.00008715611],"domain_scores_gemma":[0.9985381,0.000467277,0.0001080724,0.0001976125,0.000586149,0.000102805],"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":[0.001923662,0.001180019,0.01545587,0.0006089334,0.0005099278,0.0003514023,0.00008796174,0.6496567,0.01972623,0.001234512,0.01101358,0.2982513],"study_design_scores_gemma":[0.00008943873,0.0008023861,0.00541655,0.00003367661,0.00005822892,0.00009004853,0.00004124562,0.9804609,0.01128103,0.0004201635,0.001289408,0.00001696315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.959945,0.00136318,0.02639446,0.0005652807,0.000269177,0.0002206988,0.001183777,0.002505786,0.007552708],"genre_scores_gemma":[0.9517294,0.0003985291,0.0395738,0.0002505409,0.00004138022,0.0001640482,0.00376865,0.0001476307,0.003926088],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01067278,"threshold_uncertainty_score":0.02122134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03058053254671939,"score_gpt":0.2616409753011994,"score_spread":0.23106044275448,"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."}}