{"id":"W4285181047","doi":"10.1109/lgrs.2022.3173052","title":"Remote Sensing Image Classification Using CNNs With Balanced Gradient for Distributed Heterogeneous Computing","year":2022,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Regional Development Fund; Junta de Extremadura; Horizon 2020 Framework Programme; CODE; Ministerio de Ciencia e Innovación","keywords":"Computer science; Symmetric multiprocessor system; Workload; Heterogeneous network; Deep learning; Contextual image classification; Feature extraction; Convolutional neural network; Distributed computing; Artificial intelligence; Feature (linguistics); Speedup; Supercomputer; Machine learning; Data mining; Image (mathematics); Parallel computing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002506906,0.0006240137,0.0003496229,0.0003911242,0.000219428,0.0006179076,0.0009144938,0.0003859648,0.001217211],"category_scores_gemma":[0.0006812185,0.0002017955,0.0003306621,0.0004463217,0.0002681592,0.0008336612,0.0005660211,0.0005011239,0.0004120508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001046687,"about_ca_system_score_gemma":0.0007152481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01450693,"about_ca_topic_score_gemma":0.01795157,"domain_scores_codex":[0.9998661,0.00001239367,0.000006076555,0.00003742209,0.00004368224,0.00003430558],"domain_scores_gemma":[0.9998766,0.00002307746,0.00001712033,0.00002735468,0.00004284483,0.0000130343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000215253,0.0001436131,0.002814029,0.00007558281,0.00009469058,0.0001270739,0.00005507794,0.6736813,0.02405322,0.008161368,0.003649307,0.2869295],"study_design_scores_gemma":[0.000002306839,0.000009952584,0.0002155495,0.000001783263,0.000004080498,0.000007764707,0.00000398298,0.9964386,0.001962207,0.001024312,0.0003275919,0.00000184784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1381563,0.0006179152,0.8521078,0.0003923076,0.0001173012,0.00009346583,0.000222499,0.002541885,0.005750635],"genre_scores_gemma":[0.8781904,0.0002066553,0.1176217,0.0001128675,0.00003569905,0.00006775955,0.0003726422,0.00008864219,0.003303629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01450693,"threshold_uncertainty_score":0.02884501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02173706144940345,"score_gpt":0.2366193409364543,"score_spread":0.2148822794870508,"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."}}