{"id":"W4317384342","doi":"10.1109/access.2023.3237966","title":"A Cross-Modal Alignment for Zero-Shot Image Classification","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Natural Resources","keywords":"Computer science; Matching (statistics); Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Embedding; Metric (unit); Modal; Feature extraction; Zero (linguistics); Image (mathematics); Encoder; Contextual image classification; Measure (data warehouse); Key (lock); Data mining; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004410184,0.000106726,0.0001063562,0.0001323107,0.0002330466,0.0009859358,0.001032792,0.00005043317,0.00002653597],"category_scores_gemma":[0.00006754377,0.0001052082,0.00006924476,0.0005459608,0.00004328067,0.001152928,0.0001264261,0.00007554317,0.0003172847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000473944,"about_ca_system_score_gemma":0.00005336947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001219654,"about_ca_topic_score_gemma":0.000002508535,"domain_scores_codex":[0.9987767,0.00003675634,0.0002222726,0.0003856994,0.0002773257,0.0003012518],"domain_scores_gemma":[0.9991444,0.0001468723,0.000109368,0.0004007465,0.0001125925,0.00008599781],"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":[0.0001654099,0.0004052226,0.01233981,0.0002938031,0.0001499629,0.00007720072,0.007088401,0.01563099,0.241927,0.2607931,0.1215313,0.3395978],"study_design_scores_gemma":[0.001564095,0.00009707495,0.09919173,0.00002821788,0.00001008357,0.000006519555,0.0001041788,0.7778376,0.02243271,0.01767435,0.08054402,0.0005094082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0525616,0.000008621295,0.9406945,0.001252929,0.0009422214,0.0003062956,0.00000609777,0.0004479351,0.003779841],"genre_scores_gemma":[0.9861192,0.000009212094,0.010182,0.0005847584,0.0001255177,0.0001782042,0.00001989332,0.00001620324,0.002765078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335575,"threshold_uncertainty_score":0.9507402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1308000278195402,"score_gpt":0.4054642342831136,"score_spread":0.2746642064635734,"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."}}