{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001647303,0.0003337878,0.000564964,0.0006737707,0.0001637922,0.0001649351,0.0002442202,0.0002715153,0.00003201295],"category_scores_gemma":[0.0005909881,0.0002560301,0.0001747414,0.0003275312,0.0006054311,0.00005875966,0.0001058458,0.0009628961,0.000007789828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000140999,"about_ca_system_score_gemma":0.0002525526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002714315,"about_ca_topic_score_gemma":0.00001280757,"domain_scores_codex":[0.9972661,0.00004584898,0.0004326105,0.00106413,0.0008223349,0.0003689554],"domain_scores_gemma":[0.9984182,0.0007670649,0.00007973876,0.0003265781,0.000212671,0.0001957134],"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":[0.0001486849,0.00008168034,0.00004135594,0.0009105697,0.0001343851,0.0001698772,0.001514421,0.01192078,0.01279,0.003589639,0.0000542866,0.9686443],"study_design_scores_gemma":[0.0005079953,0.0002702418,0.0001052852,0.001177629,0.0002431189,0.0001326367,0.00000142742,0.9883168,0.001251487,0.007110583,0.0006100558,0.0002727802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00195918,0.0005572085,0.9895849,0.00651833,0.0002747063,0.0005052774,0.000004462626,0.0001063836,0.0004895104],"genre_scores_gemma":[0.5183694,0.00004405634,0.477039,0.0007404229,0.0007571039,0.00005457321,0.00009035091,0.00008266215,0.002822446],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.976396,"threshold_uncertainty_score":0.9999892,"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."}}