{"id":"W3094695322","doi":"10.1109/lgrs.2020.3033149","title":"Depthwise Separable ResNet in the MAP Framework for Hyperspectral Image Classification","year":2020,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Hyperspectral imaging; Overfitting; Convolution (computer science); Residual neural network; Contextual image classification; Convolutional neural network; Pointwise; Spatial analysis; Decision boundary; Artificial neural network; Image (mathematics); Mathematics; Remote sensing; Support vector machine; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003363775,0.0001631561,0.0001501057,0.00008135236,0.0001684378,0.0002066882,0.0001825373,0.00008379277,7.054966e-7],"category_scores_gemma":[0.0001615585,0.0001358667,0.00004828162,0.0004167421,0.0002316588,0.0002169168,0.000008974884,0.0002892456,0.00001345785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006019132,"about_ca_system_score_gemma":0.00001667941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004633474,"about_ca_topic_score_gemma":0.00001251473,"domain_scores_codex":[0.9987682,0.00005589758,0.0002221699,0.0003664014,0.0002079675,0.0003793902],"domain_scores_gemma":[0.9993695,0.0001935826,0.0000507265,0.0002786313,0.00003123657,0.00007633746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001626468,0.00000455491,0.00001204441,0.00006669288,0.000005191169,0.00002163823,0.002670424,0.001404876,0.9585831,0.00008236996,0.004562211,0.03257059],"study_design_scores_gemma":[0.0001919838,0.00002354868,0.001864655,0.00007435603,0.00001458822,0.00003077981,0.0006217393,0.9838263,0.009710102,0.0007351898,0.002676924,0.0002297981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3635122,0.00006970741,0.5987359,0.03654729,0.0004446568,0.000338245,0.00000309703,0.0001313869,0.0002175701],"genre_scores_gemma":[0.684849,0.00004725531,0.3099535,0.004800648,0.0003006842,3.297079e-7,0.000007700818,0.00002962613,0.00001122482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9824215,"threshold_uncertainty_score":0.5540482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0338131722686948,"score_gpt":0.2607173746625963,"score_spread":0.2269042023939015,"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."}}