{"id":"W4403976877","doi":"10.1109/lgrs.2024.3489634","title":"Generalized Few-Shot Semantic Segmentation in Remote Sensing: Challenge and Benchmark","year":2024,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Fusion Oriented REsearch for disruptive Science and Technology","keywords":"Computer science; Benchmark (surveying); Segmentation; Shot (pellet); Artificial intelligence; Remote sensing; Image segmentation; Computer vision; Geology; Geodesy","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":[0.0005680902,0.000239485,0.0002390719,0.0004499842,0.0002214459,0.0004877662,0.0001928131,0.00007965139,6.295883e-7],"category_scores_gemma":[0.00004096238,0.0002130392,0.00004778245,0.0008938438,0.0002630219,0.0008706242,0.0001255602,0.0002619447,0.000004484916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006830847,"about_ca_system_score_gemma":0.00004137495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004470914,"about_ca_topic_score_gemma":0.00004290778,"domain_scores_codex":[0.9979622,0.0001016372,0.0002967739,0.0008385322,0.0003297128,0.0004711824],"domain_scores_gemma":[0.9993274,0.0001185329,0.00006709068,0.000336443,0.00003736083,0.0001131642],"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":[0.000004342252,0.000002568586,0.000002604876,0.00005231211,0.000004328166,0.0003604535,0.0009839534,0.000009684541,0.2188527,0.00007917352,0.000141012,0.7795069],"study_design_scores_gemma":[0.000313954,0.00009797091,0.0002274269,0.0006562863,0.00001460469,0.000567694,0.00007590678,0.9375151,0.0513931,0.006549537,0.002087175,0.0005012567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2345539,0.0007817071,0.7570739,0.006521903,0.0005514584,0.0001831133,6.462759e-7,0.0002198947,0.0001134834],"genre_scores_gemma":[0.3682179,0.00215713,0.6251981,0.004062719,0.0001636826,4.891711e-8,0.000002391973,0.00002365011,0.0001744446],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9375054,"threshold_uncertainty_score":0.8687487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0248971065725083,"score_gpt":0.2894295262974094,"score_spread":0.264532419724901,"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."}}