{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004807936,0.0003376131,0.0003218139,0.0002342909,0.001185243,0.0002427056,0.0001639628,0.00006142561,5.777594e-7],"category_scores_gemma":[0.0000517989,0.000345635,0.00008457946,0.0006596457,0.0003478315,0.000195393,0.00005524642,0.0003325908,0.000001474105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004881798,"about_ca_system_score_gemma":0.00004550273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000173907,"about_ca_topic_score_gemma":0.0000185815,"domain_scores_codex":[0.9976228,0.0001073068,0.0004159287,0.0006994302,0.0004330734,0.0007214749],"domain_scores_gemma":[0.9989283,0.0001349883,0.000206212,0.0004702942,0.000117824,0.0001423957],"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":[0.00002511386,0.000004094459,0.00000449256,0.00004834741,0.00001923653,0.00005311388,0.0003730642,0.09129839,0.7803482,8.04437e-7,0.0001309392,0.1276941],"study_design_scores_gemma":[0.0004490654,0.00005227372,0.0003479336,0.000106572,0.00004790723,0.0009904114,0.000254135,0.9811837,0.01548514,0.00003559488,0.0006031613,0.000444096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4762225,0.00001975066,0.5221587,0.0005182082,0.0005632955,0.0002728627,0.00001619071,0.000215402,0.00001313681],"genre_scores_gemma":[0.7030558,0.000007940536,0.2962686,0.0004203452,0.0001313443,4.499671e-8,0.00004364977,0.00006275356,0.000009565818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8898853,"threshold_uncertainty_score":0.9998996,"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."}}