{"id":"W4388535692","doi":"10.21203/rs.3.rs-3557409/v1","title":"Transductive Meta-Learning with Enhanced Feature Ensemble for Few-shot Semantic Segmentation","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Pascal (unit); Segmentation; Benchmark (surveying); Pattern recognition (psychology); Matching (statistics); Machine learning; Shot (pellet); Extractor; Feature (linguistics); Class (philosophy)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001611935,0.001816461,0.002128541,0.001490102,0.0006056839,0.001080688,0.003238976,0.002159185,0.001852525],"category_scores_gemma":[0.003208527,0.000686433,0.001460015,0.00109719,0.001119616,0.003044332,0.001949886,0.002743728,0.0009109938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00122925,"about_ca_system_score_gemma":0.0008366434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003739918,"about_ca_topic_score_gemma":0.005059,"domain_scores_codex":[0.9989599,0.0002251104,0.00004053219,0.0004413535,0.0001967039,0.0001364419],"domain_scores_gemma":[0.9986742,0.0005137647,0.0001047004,0.0003179074,0.0003023458,0.00008713796],"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":[0.0003792096,0.0005156925,0.002214441,0.0001541508,0.0003031568,0.0002170787,0.000211644,0.4355876,0.02482848,0.005781142,0.005582377,0.5242251],"study_design_scores_gemma":[0.000004081257,0.00004549084,0.0001596456,0.000005051502,0.00001367272,0.00002470374,0.00001144799,0.992442,0.003476184,0.003549381,0.0002610645,0.000007393959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04218388,0.0005563782,0.9504715,0.0002311753,0.00007811999,0.0000791823,0.000171476,0.004787004,0.001441393],"genre_scores_gemma":[0.7291321,0.0002199916,0.2638357,0.0005536073,0.0001196486,0.0001709897,0.001367796,0.0004245488,0.004175601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003739918,"threshold_uncertainty_score":0.008918941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1850342493475725,"score_gpt":0.4148479433312821,"score_spread":0.2298136939837095,"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."}}