{"id":"W3173994423","doi":"10.1109/tgrs.2021.3080580","title":"BDANet: Multiscale Convolutional Neural Network With Cross-Directional Attention for Building Damage Assessment From Satellite Images","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Natural Resources and Forestry","funders":"Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou); National Natural Science Foundation of China","keywords":"Convolutional neural network; Computer science; Deep learning; Satellite; Artificial intelligence; Stage (stratigraphy); Artificial neural network; Satellite imagery; Scale (ratio); Feature (linguistics); Representation (politics); Remote sensing; Data mining; Machine learning; Cartography; Geography; Engineering; Geology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003147492,0.0004392519,0.0003916566,0.0001842827,0.0007545965,0.0007039707,0.0001303243,0.0002900858,0.000005897256],"category_scores_gemma":[0.00000992973,0.0004439621,0.0001750738,0.0002985322,0.0004005272,0.0003575633,0.000009272764,0.0008124702,0.000001684974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002939505,"about_ca_system_score_gemma":0.0001319822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003662904,"about_ca_topic_score_gemma":0.0002187657,"domain_scores_codex":[0.9975727,0.00008683337,0.000450787,0.0009345571,0.0004552485,0.0004998972],"domain_scores_gemma":[0.9987038,0.0002759189,0.0001553004,0.0004300808,0.0002911465,0.0001437554],"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":[0.00003635463,0.00002449051,0.00003162786,0.0001095648,0.00008907034,0.00001842564,0.00008484441,0.6628942,0.09675903,0.000001382827,0.00001650865,0.2399345],"study_design_scores_gemma":[0.000433029,0.00003690187,0.02798075,0.0006493862,0.0001125681,0.00007529867,0.00007482065,0.9582049,0.0117141,0.0001249106,0.0001113457,0.0004820084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3146308,0.0001772563,0.6820294,0.0001118247,0.002297966,0.0003606409,0.00009177717,0.0002372061,0.00006305911],"genre_scores_gemma":[0.5500886,0.0002282823,0.449072,0.00003334146,0.0002579177,0.000001253485,0.0001021363,0.00005399195,0.0001624476],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2953107,"threshold_uncertainty_score":0.9998012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01799424995182074,"score_gpt":0.274101724573745,"score_spread":0.2561074746219242,"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."}}