{"id":"W4392293106","doi":"10.1007/s00521-024-09471-x","title":"A lightweight siamese transformer for few-shot semantic segmentation","year":2024,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Liaoning Province","keywords":"Computer science; Transformer; Segmentation; Pascal (unit); Artificial intelligence; Information retrieval; Voltage; Programming language","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":[0.001019514,0.001165248,0.001925403,0.001523306,0.0006080733,0.001569131,0.00276496,0.001649521,0.01289754],"category_scores_gemma":[0.002807187,0.0005886048,0.001223449,0.00181003,0.0006273402,0.003058167,0.002989376,0.00255994,0.007443724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006994978,"about_ca_system_score_gemma":0.00196944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006508088,"about_ca_topic_score_gemma":0.01341005,"domain_scores_codex":[0.999211,0.0001134901,0.00005042785,0.0002859732,0.0002380884,0.0001010884],"domain_scores_gemma":[0.9991751,0.000218212,0.00003540773,0.0002598552,0.0002262434,0.00008522028],"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":[0.0004727588,0.0002961046,0.0004180003,0.0001921306,0.0001289267,0.000130549,0.00006545019,0.02765275,0.03540379,0.01541695,0.01467126,0.9051512],"study_design_scores_gemma":[0.00003180232,0.00008361498,0.0002797512,0.00001670064,0.00004023896,0.0002141252,0.00004202097,0.9494839,0.01785583,0.02681501,0.005111243,0.00002569229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003431281,0.0002632678,0.9902511,0.00007981544,0.00008450128,0.00007146195,0.0002553987,0.004441922,0.001121227],"genre_scores_gemma":[0.1730145,0.0006050395,0.8114671,0.0004496464,0.0001491088,0.0002058288,0.003497047,0.001274666,0.009337028],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01289754,"threshold_uncertainty_score":0.04314649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02666150186036346,"score_gpt":0.3091090357777974,"score_spread":0.2824475339174339,"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."}}