{"id":"W3174951629","doi":"10.5194/isprs-archives-xliii-b3-2021-829-2021","title":"EVALUATION OF SEMI-SUPERVISED LEARNING FOR CNN-BASED CHANGE DETECTION","year":2021,"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":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Change detection; Consistency (knowledge bases); Segmentation; Machine learning; Supervised learning; Pattern recognition (psychology); Image (mathematics); Deep learning; Artificial neural network","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":[0.005627455,0.001650346,0.001074615,0.0009862793,0.0005074558,0.0008438359,0.002307903,0.001549265,0.001711676],"category_scores_gemma":[0.01212963,0.0004660273,0.0008360541,0.0006159006,0.0008266037,0.0015918,0.001134309,0.001336934,0.0008050381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00137173,"about_ca_system_score_gemma":0.001314871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007417545,"about_ca_topic_score_gemma":0.0101256,"domain_scores_codex":[0.9975068,0.001028614,0.0001595946,0.0006197084,0.000514799,0.0001704995],"domain_scores_gemma":[0.9918188,0.003717038,0.0007137411,0.001086466,0.002340785,0.0003231507],"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":[0.002396712,0.001338913,0.01804709,0.0007976832,0.0008579465,0.0002044141,0.0001656505,0.6174095,0.01361688,0.001215784,0.008105785,0.3358437],"study_design_scores_gemma":[0.00002035729,0.0001532615,0.001099012,0.00001258425,0.0000194918,0.00003623568,0.00001417386,0.9937534,0.004357019,0.0002781779,0.0002495728,0.000006761647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6511742,0.002631312,0.3236355,0.0005478055,0.0005008066,0.000748362,0.001520993,0.01325596,0.005985],"genre_scores_gemma":[0.9306671,0.0001928333,0.0630753,0.0001749626,0.00005378782,0.000180241,0.003593952,0.0002400925,0.001821705],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007417545,"threshold_uncertainty_score":0.0297612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04011460378438498,"score_gpt":0.2738229588430396,"score_spread":0.2337083550586546,"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."}}