{"id":"W4386923814","doi":"10.11834/jig.220799","title":"Survey on Transformer for image classification","year":2023,"lang":"en","type":"article","venue":"Journal of Image and Graphics","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Transformer; Image processing; Convolutional neural network; Contextual image classification; Deep learning; Computer vision; Pattern recognition (psychology); Machine learning; Image (mathematics); Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001116519,0.00009225956,0.0001628248,0.0003103324,0.00009995187,0.0001188052,0.0002812419,0.0000489077,9.902079e-7],"category_scores_gemma":[0.0002612061,0.00007128778,0.0001082015,0.0006327272,0.00006121564,0.0008859321,0.00001527713,0.0001701099,0.000003111837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008968354,"about_ca_system_score_gemma":0.00003546641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002442952,"about_ca_topic_score_gemma":0.00000250476,"domain_scores_codex":[0.9991651,0.00004668417,0.0002911528,0.0001337083,0.0002032223,0.0001601503],"domain_scores_gemma":[0.998854,0.0003350292,0.0001764819,0.0001609026,0.0004004696,0.00007309513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003542138,0.0003247419,0.003075083,0.0001984149,0.0001441096,0.0001529314,0.001078613,0.000002482022,0.1734385,0.05129042,0.1088373,0.6611032],"study_design_scores_gemma":[0.003059832,0.004143031,0.5281773,0.0002628782,0.00006742869,0.0001625267,0.0001624517,0.01167768,0.2259287,0.1780791,0.04742511,0.0008539173],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009391859,0.0001334852,0.9885556,0.001464972,0.0001144994,0.0001236123,0.00001542329,0.00005894055,0.0001415805],"genre_scores_gemma":[0.7961423,0.01093739,0.1903538,0.001753776,0.0003211086,0.00001787904,0.00002693383,0.00005087637,0.0003959104],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7982018,"threshold_uncertainty_score":0.2907031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0559637684887457,"score_gpt":0.3454678466378371,"score_spread":0.2895040781490914,"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."}}