{"id":"W3047113081","doi":"10.5194/isprs-archives-xlii-3-w12-2020-183-2020","title":"APPLICATION OF SEMANTIC SEGMENTATION WITH FEW LABELS IN THE DETECTION OF WATER BODIES FROM PERUSAT-1 SATELLITE’S IMAGES","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 and LiDAR Applications","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Servicio Nacional de Capacitación para la Industria de la Construcción","keywords":"Computer science; Convolutional neural network; Satellite; Segmentation; Task (project management); Artificial intelligence; Transfer of learning; Process (computing); Remote sensing; Flood myth; Pattern recognition (psychology); Computer vision; Geography","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":[0.0008400244,0.0008981802,0.0003656766,0.001793842,0.0004256102,0.0006572229,0.0005568086,0.001164795,0.0009123642],"category_scores_gemma":[0.001818058,0.0002380625,0.0005194333,0.000983588,0.0004502454,0.0009750103,0.000561234,0.0004356843,0.0003311902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006443734,"about_ca_system_score_gemma":0.000657727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02183173,"about_ca_topic_score_gemma":0.0299237,"domain_scores_codex":[0.9996492,0.0001123583,0.00001798257,0.0001188607,0.0000489946,0.00005263506],"domain_scores_gemma":[0.9994602,0.0002353771,0.00004829506,0.00007677126,0.000148784,0.00003060146],"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":[0.001394614,0.0008419752,0.04799206,0.0004404622,0.0003328863,0.0006725265,0.0006709848,0.2901974,0.0773733,0.001293824,0.005017379,0.5737725],"study_design_scores_gemma":[0.00001155939,0.0001097646,0.01235074,0.00002055194,0.00004650567,0.0000566397,0.0002308989,0.970888,0.01487025,0.0005503376,0.0008502529,0.00001452946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9120823,0.0005150555,0.08222293,0.0002596058,0.00005249338,0.00009002945,0.0004763975,0.001476011,0.002825068],"genre_scores_gemma":[0.957544,0.0001294149,0.03959461,0.00005298301,0.000016691,0.00003488021,0.001385248,0.00004769233,0.001194569],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02183173,"threshold_uncertainty_score":0.04340929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0123662403592507,"score_gpt":0.2349667208743128,"score_spread":0.2226004805150621,"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."}}