{"id":"W4392942841","doi":"10.1109/icmla58977.2023.00041","title":"Improving Adversarial Robustness of Few-Shot Learning with Contrastive Learning and Hypersphere Embedding","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hypersphere; Adversarial system; Robustness (evolution); Embedding; Computer science; Artificial intelligence","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":[0.002278891,0.00129208,0.001157412,0.000740052,0.0004745882,0.0008872413,0.001555886,0.001453634,0.001078179],"category_scores_gemma":[0.007569021,0.0003632677,0.0007110372,0.0003635251,0.001679684,0.002421107,0.002365067,0.002363163,0.0003315924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009711795,"about_ca_system_score_gemma":0.000736649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002490151,"about_ca_topic_score_gemma":0.002294321,"domain_scores_codex":[0.9991505,0.0002502593,0.00003658287,0.0002407696,0.0002273898,0.00009452712],"domain_scores_gemma":[0.9974036,0.00135045,0.0002584981,0.0005398482,0.0003107363,0.0001369977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002294418,0.0002332053,0.002031581,0.0001026676,0.0001164533,0.0001890814,0.0001332586,0.8552741,0.01611816,0.01032202,0.002068272,0.1131818],"study_design_scores_gemma":[0.000003728494,0.00006031761,0.0001668852,0.000004725166,0.000004769479,0.00003673131,0.000008250249,0.9937139,0.002956144,0.002862636,0.0001754023,0.000006401098],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1327008,0.0008114434,0.8614897,0.0004983247,0.0001059466,0.0001064914,0.0001061363,0.001384882,0.002796191],"genre_scores_gemma":[0.9220517,0.0002151449,0.07455824,0.0002895809,0.00005475962,0.0000627975,0.0002945532,0.000106767,0.002366445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002490151,"threshold_uncertainty_score":0.01205206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01430306757815698,"score_gpt":0.249969221976751,"score_spread":0.235666154398594,"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."}}