{"id":"W4391922244","doi":"10.1038/s41598-024-54640-6","title":"Transductive meta-learning with enhanced feature ensemble for few-shot semantic segmentation","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Shot (pellet); Feature (linguistics); Ensemble learning; Pattern recognition (psychology); Semantic feature; Machine learning","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":[0.001348313,0.00212073,0.002027785,0.001430522,0.0006216075,0.001170929,0.003556897,0.002103071,0.002127824],"category_scores_gemma":[0.002699667,0.0008136344,0.001672942,0.001127265,0.001065559,0.003399412,0.001913046,0.002798334,0.001141579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314147,"about_ca_system_score_gemma":0.0009271487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004233326,"about_ca_topic_score_gemma":0.005923897,"domain_scores_codex":[0.9990789,0.0001623237,0.00003716705,0.0004193209,0.0001801985,0.0001221631],"domain_scores_gemma":[0.9990496,0.0003626485,0.00008503163,0.0002181546,0.0002139947,0.00007052598],"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":[0.0003264394,0.0004011783,0.001923963,0.0001542826,0.0002821633,0.0002549473,0.0002568533,0.434869,0.02179181,0.006878426,0.005037187,0.5278238],"study_design_scores_gemma":[0.000003739033,0.00005136836,0.0001335745,0.000005692895,0.0000157533,0.00003250088,0.00001338579,0.9912282,0.003466539,0.004682578,0.0003568479,0.00000974135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02421038,0.0004689465,0.9690918,0.000151589,0.00006236575,0.00006686671,0.0001375661,0.004563553,0.0012469],"genre_scores_gemma":[0.629548,0.00029969,0.3625905,0.0005933559,0.000126745,0.0002321918,0.001531474,0.0005644245,0.004513766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004233326,"threshold_uncertainty_score":0.009534836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03173384347846758,"score_gpt":0.2811229541598212,"score_spread":0.2493891106813536,"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."}}