{"id":"W4386170403","doi":"10.1016/j.eswa.2023.121287","title":"Consistent penalizing field loss for zero-shot image retrieval","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Discriminative model; Class (philosophy); Image retrieval; Artificial intelligence; Margin (machine learning); Image (mathematics); Matching (statistics); Inference; Field (mathematics); Similarity (geometry); Pattern recognition (psychology); Machine learning; Mathematics; Statistics","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":[0.003125819,0.0009568075,0.001517267,0.001168736,0.0004274142,0.001182123,0.002282773,0.002308903,0.003542164],"category_scores_gemma":[0.008453569,0.0005656824,0.0005871842,0.0009931286,0.001164004,0.002340021,0.001734692,0.001739247,0.001194547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009542878,"about_ca_system_score_gemma":0.001477882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004301851,"about_ca_topic_score_gemma":0.004182004,"domain_scores_codex":[0.9987442,0.0004153132,0.0000528554,0.0002123013,0.0004374946,0.0001377266],"domain_scores_gemma":[0.9969813,0.001674751,0.0001701316,0.0004916685,0.0005559119,0.0001263383],"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":[0.001181944,0.0003947864,0.0009109846,0.0004522766,0.0001541337,0.0001380644,0.00007259561,0.3557471,0.03359286,0.03239889,0.01920188,0.5557544],"study_design_scores_gemma":[0.0000216613,0.0000746872,0.0002960101,0.00001353104,0.00001501193,0.00008983498,0.000009472674,0.985531,0.003549906,0.009403179,0.0009838279,0.00001199703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009815433,0.000657837,0.9877015,0.0002788966,0.00005547206,0.00004301209,0.0001093455,0.0004932289,0.000845223],"genre_scores_gemma":[0.4345319,0.001339635,0.5447361,0.000697442,0.0003567662,0.0002081812,0.00150056,0.0005498979,0.01607952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004301851,"threshold_uncertainty_score":0.01653111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03777184491170358,"score_gpt":0.3347059052843349,"score_spread":0.2969340603726313,"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."}}