{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001675556,0.0001133656,0.0001003902,0.00009695714,0.0003562754,0.000400787,0.0001933707,0.00003591755,0.0000049881],"category_scores_gemma":[0.000006607997,0.0001024109,0.00006144285,0.0003620736,0.00003027582,0.0002260281,0.00002581233,0.0001188592,0.000025124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001625905,"about_ca_system_score_gemma":0.00002527653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003912807,"about_ca_topic_score_gemma":0.000001674518,"domain_scores_codex":[0.999089,0.00002577855,0.0001980965,0.0003731935,0.0001187068,0.0001952436],"domain_scores_gemma":[0.9994552,0.0002332957,0.00003617897,0.0001580542,0.00004062058,0.00007666611],"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":[0.000003884568,0.00003834879,0.00006613491,0.0001636801,0.00002461997,0.000002167738,0.00225305,0.001017115,0.01036852,0.2197193,0.0007546719,0.7655885],"study_design_scores_gemma":[0.0002347476,0.0000519534,0.0003452213,0.00003538961,0.00001705536,0.00002998374,0.0001087586,0.9167735,0.001139072,0.003625915,0.0774625,0.0001758958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008904914,0.000505562,0.9855211,0.00275779,0.0001429403,0.0004990688,0.000003510747,0.0004246436,0.00124041],"genre_scores_gemma":[0.9692013,0.00002228636,0.02965944,0.0004199578,0.0001685741,0.000113111,0.00001846569,0.00001324736,0.0003836686],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9602963,"threshold_uncertainty_score":0.4176195,"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."}}