{"id":"W2996255323","doi":"10.1007/978-3-030-58558-7_2","title":"Associative Alignment for Few-Shot Image Classification","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université Laval","funders":"","keywords":"Centroid; Computer science; Artificial intelligence; Pattern recognition (psychology); Associative property; Metric (unit); Feature (linguistics); Set (abstract data type); Domain (mathematical analysis); Image (mathematics); Constructive; Machine learning; Mathematics","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":[0.001437223,0.0009214586,0.002134161,0.001672413,0.0007499444,0.001085966,0.002310093,0.001835761,0.004065455],"category_scores_gemma":[0.004444762,0.0005661333,0.0008694254,0.002285127,0.0007932754,0.002995898,0.002303324,0.002085057,0.002199365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005259677,"about_ca_system_score_gemma":0.0009347947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002365211,"about_ca_topic_score_gemma":0.003615546,"domain_scores_codex":[0.9988669,0.0002650048,0.00006812809,0.0004318025,0.0002424753,0.0001257737],"domain_scores_gemma":[0.9975776,0.001102125,0.0001743581,0.0006515042,0.0003439563,0.0001505365],"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":[0.0005120314,0.0004999622,0.001536119,0.0003154214,0.0002045533,0.0001365457,0.0001154047,0.06524946,0.03141516,0.01059732,0.008094775,0.8813233],"study_design_scores_gemma":[0.00001682513,0.0001122904,0.0008441615,0.00001670946,0.00004197457,0.0001247756,0.00005109667,0.9599706,0.009828471,0.02751118,0.001463199,0.00001872829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02723132,0.0009902017,0.9680936,0.0001619921,0.0001075487,0.00005928061,0.0002283581,0.00206719,0.001060461],"genre_scores_gemma":[0.6257348,0.001076495,0.3598213,0.0004352275,0.0003924471,0.0002731596,0.003011777,0.000534666,0.008720187],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004065455,"threshold_uncertainty_score":0.01360029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06221222492084128,"score_gpt":0.3203891967185511,"score_spread":0.2581769717977098,"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."}}