{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000468229,0.001148081,0.0006388659,0.0007098169,0.0002588024,0.0004445727,0.001551606,0.0008710544,0.001910712],"category_scores_gemma":[0.0008319214,0.0003747833,0.0007353465,0.0007983959,0.0002752978,0.0009838837,0.0009885441,0.001179421,0.0006417814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009284299,"about_ca_system_score_gemma":0.0007608051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01860998,"about_ca_topic_score_gemma":0.02574938,"domain_scores_codex":[0.9997849,0.00002386088,0.00001046998,0.00008074904,0.00005644039,0.00004352177],"domain_scores_gemma":[0.9998206,0.00004921577,0.00002616329,0.00003710462,0.00004711697,0.00001975278],"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":[0.0004640709,0.0003909759,0.003272453,0.0001582573,0.0003113475,0.0002571775,0.0000567008,0.2836286,0.02936967,0.002506569,0.02674523,0.6528389],"study_design_scores_gemma":[0.00001138314,0.00003351582,0.0006755886,0.000004927181,0.0000168706,0.00002639689,0.00000397653,0.9946221,0.002900661,0.0007605643,0.0009367827,0.000007130713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2146648,0.003290965,0.7519307,0.0008901038,0.0004225092,0.0002659586,0.003708449,0.01877594,0.006050616],"genre_scores_gemma":[0.6586879,0.0008743918,0.3152743,0.0005556107,0.0001497651,0.0002405876,0.01208944,0.000320344,0.01180765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01860998,"threshold_uncertainty_score":0.03700328,"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."}}