{"id":"W3178756862","doi":"10.1109/crv52889.2021.00011","title":"Few-Shot Learning by Integrating Spatial and Frequency Representation","year":2021,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Aeronautics and Space Administration","keywords":"Computer science; Artificial intelligence; Discrete cosine transform; Representation (politics); Frequency domain; Spatial frequency; Shot (pellet); Domain (mathematical analysis); Pattern recognition (psychology); Machine learning; Transformation (genetics); Feature learning; Computer vision; Image (mathematics); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002233934,0.00009806234,0.0001103912,0.00004722159,0.0002188904,0.000381177,0.0001593732,0.00004483897,0.0002126263],"category_scores_gemma":[0.0004001723,0.00009495146,0.00003165889,0.0002973478,0.00002713859,0.000496825,0.0001317531,0.0002310316,0.0000343339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002075607,"about_ca_system_score_gemma":0.00005270818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002921233,"about_ca_topic_score_gemma":0.00008529753,"domain_scores_codex":[0.9988428,0.0001749929,0.0002027151,0.0003845775,0.0002157597,0.0001792001],"domain_scores_gemma":[0.9993846,0.0001536683,0.00008011358,0.0001924745,0.0001039991,0.00008514411],"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":[0.000005687566,0.00007104368,0.04361871,0.00002158059,0.00003940956,0.0000919985,0.007365819,0.0003652587,0.1451627,0.1845243,0.002406026,0.6163275],"study_design_scores_gemma":[0.001980165,0.0002664583,0.02451826,0.0001026455,0.00002129906,0.0002392409,0.009097423,0.8663578,0.05264158,0.01173617,0.03191691,0.001122056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02116581,0.000191525,0.9225749,0.001103292,0.0001628373,0.00005021208,3.092408e-7,0.0001950367,0.05455607],"genre_scores_gemma":[0.9032531,0.00002788059,0.09171465,0.0004695904,0.00004192559,0.000005572765,0.00001750908,0.000008010254,0.004461718],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8820873,"threshold_uncertainty_score":0.3872008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02422276533383912,"score_gpt":0.276318912616189,"score_spread":0.2520961472823499,"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."}}