{"id":"W3155131704","doi":"10.1109/lgrs.2021.3071252","title":"Land Cover Classification of Multispectral LiDAR Data With an Efficient Self-Attention Capsule Network","year":2021,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; Six Talent Peaks Project in Jiangsu Province; National Natural Science Foundation of China","keywords":"Multispectral image; Computer science; Lidar; Land cover; Remote sensing; Artificial intelligence; Robustness (evolution); Feature extraction; Feature (linguistics); Pattern recognition (psychology); Pixel; Contextual image classification; Cover (algebra); Computer vision; Land use; Geography; Image (mathematics); Engineering","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":[0.0003441089,0.0001298162,0.0001419564,0.00002821459,0.0003188718,0.00007949532,0.0001776484,0.00004911961,0.000006506083],"category_scores_gemma":[0.00001378698,0.0001086605,0.00002222435,0.0004589152,0.0003862504,0.0001842879,0.00008095131,0.0001200243,0.00002154497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004982267,"about_ca_system_score_gemma":0.00003042913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001025245,"about_ca_topic_score_gemma":0.0003217724,"domain_scores_codex":[0.9984374,0.0000852672,0.0001943611,0.000628677,0.0003502665,0.0003040398],"domain_scores_gemma":[0.9989868,0.00002917961,0.0001282861,0.0007238519,0.0000245069,0.0001073945],"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":[0.00001936913,0.00009294358,0.00338035,0.00001678827,0.00001767333,0.00003864286,0.0006498845,0.01803995,0.9154401,0.000008410569,0.0006369133,0.06165894],"study_design_scores_gemma":[0.0003210102,0.00005021505,0.1702582,0.00006180035,0.00004832285,0.0001944117,0.0001049521,0.8226691,0.004679466,0.00002401861,0.001347873,0.0002405621],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9328746,0.00001481728,0.06532149,0.001080305,0.0001559217,0.0001204944,0.000006490526,0.00004580432,0.0003801477],"genre_scores_gemma":[0.878056,0.00001762663,0.1212866,0.0004261052,0.00008570143,2.927436e-8,0.00003457156,0.00001141762,0.00008195766],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9107607,"threshold_uncertainty_score":0.4431047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01482479214530421,"score_gpt":0.2354099505975048,"score_spread":0.2205851584522006,"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."}}