{"id":"W4390591099","doi":"10.1109/lra.2024.3349812","title":"Memory-Constrained Semantic Segmentation for Ultra-High Resolution UAV Imagery","year":2024,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Semantics (computer science); Scheme (mathematics); Computation; Artificial intelligence; Image resolution; Pixel; Image segmentation; Computer vision; Computer engineering; Algorithm","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":[0.0002885924,0.0007134097,0.000715046,0.0004894865,0.0003887,0.001257162,0.00163787,0.001034592,0.002187612],"category_scores_gemma":[0.00133068,0.0004346591,0.000718961,0.0007124043,0.0007338315,0.002261549,0.001088155,0.001048952,0.000638399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00102573,"about_ca_system_score_gemma":0.000996441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01190835,"about_ca_topic_score_gemma":0.01888039,"domain_scores_codex":[0.999737,0.00004378461,0.00001358284,0.0001054611,0.00005505759,0.00004510126],"domain_scores_gemma":[0.9997271,0.00009694233,0.00003350927,0.00007266802,0.00004976182,0.00001998093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003781509,0.0001110997,0.001971272,0.0002083271,0.00009051209,0.0002499209,0.000267917,0.8163234,0.02627717,0.01753919,0.006024115,0.1305589],"study_design_scores_gemma":[0.000005201749,0.00001276208,0.0001588541,0.000004543789,0.000006383183,0.00003378894,0.0000268972,0.9899626,0.002547246,0.006248696,0.0009879088,0.000005017083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0703751,0.0009703148,0.919858,0.0004415088,0.00006616874,0.00006310856,0.0006379406,0.00471502,0.002872825],"genre_scores_gemma":[0.7186817,0.0005661538,0.2744667,0.0003269683,0.00005655551,0.0001172715,0.001653623,0.0005772547,0.003553846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01190835,"threshold_uncertainty_score":0.02367806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01421306075296817,"score_gpt":0.2581731518465156,"score_spread":0.2439600910935475,"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."}}