{"id":"W4296218625","doi":"10.1016/j.compeleceng.2022.108326","title":"TPSN: Transformer-based multi-Prototype Search Network for few-shot semantic segmentation","year":2022,"lang":"en","type":"article","venue":"Computers & Electrical Engineering","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University; Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Artificial intelligence; Encoder; Pascal (unit); Consistency (knowledge bases); Transformer; Feature extraction; Pattern recognition (psychology); Computer vision","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":[0.0005041287,0.0002075628,0.0002360231,0.0002350533,0.0004289519,0.0001532779,0.0006525458,0.00004550085,0.00001834749],"category_scores_gemma":[0.00002529547,0.0002389621,0.0001470325,0.001215062,0.00001224281,0.000194159,0.00007079369,0.0004203434,0.000007980319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002227144,"about_ca_system_score_gemma":0.0001126109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007097948,"about_ca_topic_score_gemma":6.086825e-7,"domain_scores_codex":[0.9980655,0.00008737778,0.0003064823,0.0004565548,0.0004162514,0.0006678848],"domain_scores_gemma":[0.9991305,0.0003551065,0.00005401845,0.0002465581,0.00005558911,0.0001581869],"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":[0.00003732154,0.00006847729,0.00005398161,0.00003696833,0.00002515029,0.00000948129,0.0002853771,0.945266,0.003106803,0.004085449,0.000257615,0.04676739],"study_design_scores_gemma":[0.001191218,0.000481412,0.0004143494,0.00001275794,0.000008711702,0.00001159379,0.000009995421,0.990631,0.0009212582,0.00003973227,0.005996543,0.0002814084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002389248,0.0001856362,0.9950635,0.0004087271,0.0005850672,0.000900532,0.000001993243,0.0004362733,0.00002901923],"genre_scores_gemma":[0.5838178,0.000003983639,0.4150195,0.000565983,0.0001319615,0.0003405837,0.00003373431,0.00003695508,0.00004951515],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5814285,"threshold_uncertainty_score":0.9744592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0313340015790082,"score_gpt":0.2634984340031686,"score_spread":0.2321644324241604,"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."}}