{"id":"W4403619652","doi":"10.1007/978-3-031-72390-2_12","title":"Fine-Grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-Resolution Medical Image Classification","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Transfer of learning; Resolution (logic); Artificial intelligence; Image (mathematics); Transfer (computing); Computer vision; Machine learning; Pattern recognition (psychology); Parallel computing","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":[0.001007142,0.0008616569,0.000889782,0.0005974706,0.0004863091,0.0008449954,0.002666089,0.001654163,0.007450608],"category_scores_gemma":[0.002275696,0.0004274829,0.0006943141,0.00103653,0.00053453,0.001393645,0.001954,0.001910404,0.003126545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006402703,"about_ca_system_score_gemma":0.0009791529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003800311,"about_ca_topic_score_gemma":0.004698921,"domain_scores_codex":[0.9996424,0.00006488067,0.00002253492,0.0001095148,0.0001064267,0.00005425121],"domain_scores_gemma":[0.9992402,0.0002597696,0.00005769545,0.0001909929,0.0002001132,0.00005131202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002523499,0.0001414923,0.0003191326,0.00007407421,0.00004614939,0.00006179059,0.00006696114,0.06379683,0.0356064,0.003466343,0.008120791,0.8880476],"study_design_scores_gemma":[0.00001612336,0.00004689283,0.0002484822,0.00000712788,0.00001103447,0.00004741506,0.00001436568,0.9826664,0.009953136,0.004957539,0.00201957,0.00001193485],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008612993,0.0002212005,0.9856792,0.00009423892,0.00005563061,0.00004811624,0.00008187378,0.004255062,0.0009516278],"genre_scores_gemma":[0.2101823,0.0002656876,0.7783536,0.0003705386,0.0001051439,0.0002122441,0.0005184138,0.0007986401,0.009193392],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007450608,"threshold_uncertainty_score":0.02492476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02195129917932914,"score_gpt":0.3058320243631449,"score_spread":0.2838807251838157,"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."}}