{"id":"W4313546603","doi":"10.1109/jstars.2022.3229460","title":"LRAD-Net: An Improved Lightweight Network for Building Extraction From Remote Sensing Images","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Robustness (evolution); Feature extraction; Segmentation; Artificial intelligence; Decoding methods; Pattern recognition (psychology); Block (permutation group theory); Pyramid (geometry); Aerial image; Pooling; Image segmentation; Data mining; Remote sensing; Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005088647,0.0002000169,0.000323011,0.0001996973,0.0008187053,0.000162839,0.0002809112,0.00008704775,0.00000130344],"category_scores_gemma":[0.00005262842,0.0002099851,0.0000626865,0.00119872,0.00003661338,0.0003982995,0.00008342425,0.0006868659,1.370036e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001277038,"about_ca_system_score_gemma":0.0001410254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008788222,"about_ca_topic_score_gemma":0.0001211885,"domain_scores_codex":[0.9981072,0.000109278,0.0006997192,0.0003989774,0.0003055074,0.0003793474],"domain_scores_gemma":[0.9981903,0.0003627996,0.0006340429,0.0003502022,0.0003658136,0.00009678892],"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":[0.00004793713,0.00001950712,0.00001201653,0.00000778289,0.00002950704,0.00001445114,0.000263454,0.05200409,0.2281098,0.0006781014,0.0001208145,0.7186925],"study_design_scores_gemma":[0.0006324146,0.000100643,0.001892565,0.00004864443,0.00002752295,0.0001570139,0.00004969832,0.9371476,0.01032612,0.0386437,0.01072019,0.0002538734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1741069,0.0002130368,0.8235124,0.001170808,0.0005720076,0.0003258324,0.000005631647,0.00005797964,0.00003539806],"genre_scores_gemma":[0.1653255,0.000109744,0.8333511,0.0003165182,0.0008263589,1.999527e-7,0.00001100694,0.00002420487,0.00003533526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8851435,"threshold_uncertainty_score":0.8562945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02526952558198348,"score_gpt":0.265282410440372,"score_spread":0.2400128848583886,"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."}}