{"id":"W4285817307","doi":"10.1109/acctcs53867.2022.00074","title":"Multi-dimensional Attention UNet with Variable Size Convolution Group for Road Segmentation in Remote Sensing Imagery","year":2022,"lang":"en","type":"article","venue":"2022 2nd Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS)","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Feature (linguistics); Convolution (computer science); Decoding methods; Feature extraction; Segmentation; Variable (mathematics); Artificial intelligence; Remote sensing; Representation (politics); Pattern recognition (psychology); Data mining; Computer vision; Geography; Algorithm; Mathematics; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006081209,0.0001659726,0.0001730339,0.0006735123,0.001030135,0.00008638059,0.0005034649,0.00008776884,0.0000179517],"category_scores_gemma":[0.00002041242,0.0001740006,0.0000230035,0.001547491,0.0004793789,0.0003541957,0.0003128434,0.0004919452,0.000002604959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002169678,"about_ca_system_score_gemma":0.00008593925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004030323,"about_ca_topic_score_gemma":0.00003311133,"domain_scores_codex":[0.9987628,0.00007161175,0.0002669857,0.0003963505,0.0002113029,0.000290935],"domain_scores_gemma":[0.9989823,0.0001041843,0.0001084402,0.0006574627,0.0001076861,0.000039946],"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":[0.00009574789,0.0003639391,0.0006676334,0.00006163225,0.00005854676,0.000008834651,0.0006389546,0.02437649,0.3642157,0.04229682,0.0003805934,0.5668351],"study_design_scores_gemma":[0.000616245,0.0001640124,0.00206232,0.00007170334,0.00001250641,0.0000930808,0.0008651595,0.9928824,0.0006435491,0.001512661,0.0008637471,0.000212624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.318586,0.000248699,0.6768238,0.001526652,0.0006018315,0.0008051996,0.00003123533,0.000790345,0.0005862411],"genre_scores_gemma":[0.8059707,0.00005832492,0.1937692,0.00002420236,0.000009720644,0.0000400565,0.00005636858,0.00001224008,0.00005920494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9685059,"threshold_uncertainty_score":0.7923072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01550572440919512,"score_gpt":0.2478782929968179,"score_spread":0.2323725685876228,"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."}}