{"id":"W2745252301","doi":"10.1109/igarss.2017.8127330","title":"Deep residual networks for hyperspectral image classification","year":2017,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Residual; Computer science; Artificial intelligence; Convolutional neural network; Normalization (sociology); Hyperspectral imaging; Deep learning; Pattern recognition (psychology); Contextual image classification; Embedding; Regularization (linguistics); Deep neural networks; Dimensionality reduction; Feature learning; Image (mathematics); Algorithm","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":[0.0007099251,0.0008386269,0.0004662821,0.0005664382,0.000228149,0.0005707211,0.0008211543,0.0005942701,0.001766939],"category_scores_gemma":[0.00147063,0.0002616853,0.0005589456,0.0006792668,0.0003548346,0.001017037,0.0006179841,0.001200368,0.0007133037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006061257,"about_ca_system_score_gemma":0.0005676886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006155328,"about_ca_topic_score_gemma":0.007643255,"domain_scores_codex":[0.999686,0.00006436519,0.00001910242,0.00008162941,0.0001072095,0.00004173188],"domain_scores_gemma":[0.9996247,0.0001220358,0.00006531734,0.00006444799,0.0001070373,0.00001649089],"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":[0.0001738801,0.0001978542,0.002460395,0.000161394,0.0001369745,0.0000919747,0.00007085834,0.442743,0.02863376,0.01013488,0.006520733,0.5086743],"study_design_scores_gemma":[0.000003189624,0.00002436734,0.000440958,0.000007746209,0.000007805787,0.0000135208,0.000008246064,0.9896832,0.005520069,0.003232035,0.001051961,0.000006849984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05690618,0.001966902,0.9335151,0.000442067,0.00009468024,0.00005524736,0.0004421856,0.003202202,0.003375384],"genre_scores_gemma":[0.6880141,0.00124008,0.300618,0.0002459959,0.0000880854,0.0001306983,0.001979667,0.000217311,0.007465971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006155328,"threshold_uncertainty_score":0.01223904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03160568644587343,"score_gpt":0.2710259716334991,"score_spread":0.2394202851876257,"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."}}