{"id":"W4386100208","doi":"10.1007/s13735-023-00286-5","title":"CoCoOpter: Pre-train, prompt, and fine-tune the vision-language model for few-shot image classification","year":2023,"lang":"en","type":"article","venue":"International Journal of Multimedia Information Retrieval","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Overfitting; Artificial intelligence; Convolutional neural network; Generalizability theory; Classifier (UML); Pattern recognition (psychology); Transfer of learning; Contextual image classification; Machine learning; Artificial neural network; Image (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":[0.001182958,0.002446887,0.001834017,0.001273762,0.0007456196,0.00110355,0.003807579,0.001866967,0.008276684],"category_scores_gemma":[0.002964971,0.0008159559,0.001158928,0.001092958,0.0004996264,0.002214375,0.002256647,0.003091472,0.005779997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009143261,"about_ca_system_score_gemma":0.002430629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0170723,"about_ca_topic_score_gemma":0.03410321,"domain_scores_codex":[0.9992693,0.00007119775,0.00003189795,0.0003379169,0.0001499966,0.0001396254],"domain_scores_gemma":[0.9990006,0.000328804,0.00003992758,0.0002209236,0.0002774308,0.0001322954],"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":[0.0009523157,0.0009170633,0.001702611,0.0003290174,0.0002679117,0.0002590548,0.00008982182,0.02456025,0.04323395,0.001128117,0.06936525,0.8571947],"study_design_scores_gemma":[0.0001263442,0.0002347179,0.0008274782,0.00002022738,0.00006071186,0.0001575648,0.00006614256,0.9597429,0.02964624,0.003226578,0.005840906,0.00005010766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04432603,0.001719611,0.8149218,0.0003774838,0.0008191183,0.000485628,0.002727418,0.1321014,0.002521461],"genre_scores_gemma":[0.3001946,0.0006200728,0.6600128,0.001686827,0.0002163009,0.0009398317,0.01676976,0.005281255,0.01427845],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0170723,"threshold_uncertainty_score":0.03394586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02849561482367897,"score_gpt":0.3338832349282922,"score_spread":0.3053876201046133,"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."}}