{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001417067,0.000121912,0.0001038876,0.0001185965,0.0001800528,0.0002712243,0.0001446693,0.0000371795,0.000001618181],"category_scores_gemma":[0.0000123889,0.0001213984,0.00004588832,0.0002965763,0.00005364351,0.0006264102,0.00001502925,0.00007589911,0.00001536884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004942373,"about_ca_system_score_gemma":0.00002111162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003306499,"about_ca_topic_score_gemma":0.000001285035,"domain_scores_codex":[0.9990595,0.00002718695,0.0002361111,0.0003403506,0.0001415012,0.0001953396],"domain_scores_gemma":[0.9994235,0.0002161949,0.0000711304,0.0002013152,0.00003701344,0.00005082913],"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":[0.000003835024,0.0000260055,0.000007280121,0.0001810979,0.00003678884,0.000009270758,0.0004358435,0.4525373,0.408593,0.05876108,0.007874589,0.07153392],"study_design_scores_gemma":[0.0002110485,0.00002302235,0.0002086271,0.00005373143,0.00002144166,0.00002468993,0.00001207002,0.9788913,0.015673,0.004469364,0.0002415526,0.0001701532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01116286,0.00007460253,0.9689734,0.01822358,0.0006447243,0.0004351769,0.000008100189,0.0004521189,0.00002544997],"genre_scores_gemma":[0.715036,0.00003018262,0.2832046,0.001334446,0.0001889839,0.00009405199,0.00003512776,0.00001594324,0.00006058899],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7038732,"threshold_uncertainty_score":0.4950482,"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."}}