{"id":"W4280544949","doi":"10.5194/isprs-annals-v-3-2022-17-2022","title":"HOW FAR SHOULD I LOOK? A NEURAL ARCHITECTURE SEARCH STRATEGY FOR SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGES","year":2022,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pruning; Artificial intelligence; Artificial neural network; Segmentation; Pixel; Pattern recognition (psychology); Feature (linguistics); Network architecture; Set (abstract data type); Space (punctuation); Architecture; Data mining; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001116691,0.0002076446,0.0002882888,0.0004186143,0.0005320985,0.0003035901,0.0002330667,0.00006299638,0.000001596428],"category_scores_gemma":[0.0002436263,0.0001717658,0.000151226,0.0008576821,0.0003409951,0.0003210597,0.0001037498,0.0002671214,2.683939e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003303115,"about_ca_system_score_gemma":0.00006113043,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.011681,"about_ca_topic_score_gemma":0.0006949523,"domain_scores_codex":[0.9980462,0.000151072,0.0005269899,0.0002010768,0.0007171219,0.0003575071],"domain_scores_gemma":[0.9988073,0.0001719198,0.0003488944,0.000294429,0.0003183415,0.00005917885],"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":[0.00002780804,0.000003324042,0.000004558816,0.0001345343,0.00001963863,3.345572e-7,0.0008908996,0.08945421,0.04558469,0.000001290632,0.0000878366,0.8637909],"study_design_scores_gemma":[0.0001938345,0.0001317236,0.0001808976,0.00004940005,0.00001928468,0.00004283652,0.00249233,0.84242,0.1533773,0.0002838018,0.0006574668,0.0001511036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1440803,0.0001179577,0.852914,0.001694949,0.0003523353,0.0005479574,0.00004634133,0.00006874007,0.0001773757],"genre_scores_gemma":[0.9857521,0.00004651941,0.01391926,0.0001852015,0.00003307094,1.021814e-7,0.00002193193,0.00001676996,0.00002504396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8636398,"threshold_uncertainty_score":0.9949003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08062477983877343,"score_gpt":0.3188091837695575,"score_spread":0.238184403930784,"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."}}