{"id":"W4385260955","doi":"10.48550/arxiv.2307.11808","title":"Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Artificial intelligence; Classifier (UML); Bilevel optimization; Affine transformation; Machine learning; Pattern recognition (psychology); Transformation (genetics); Deep learning; Optimization problem; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001243523,0.001288407,0.001256751,0.0006332549,0.0003531028,0.001311056,0.001488122,0.001665672,0.001826914],"category_scores_gemma":[0.003835091,0.0008479434,0.001328452,0.000597127,0.001125392,0.001214547,0.00159499,0.002786381,0.0008683839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009803333,"about_ca_system_score_gemma":0.001425722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004996781,"about_ca_topic_score_gemma":0.005192671,"domain_scores_codex":[0.9995742,0.0001111641,0.00002806637,0.0001403301,0.00008582348,0.00006031018],"domain_scores_gemma":[0.9989446,0.0005525636,0.0001063416,0.00014575,0.000195997,0.00005481234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001127653,0.00008780412,0.0009216464,0.0001065513,0.00004494996,0.00008757766,0.00008455862,0.903371,0.007108639,0.002578854,0.001751767,0.0837438],"study_design_scores_gemma":[0.000003722877,0.00001160331,0.00004803831,0.00000552336,0.000002626979,0.00001054163,0.00000464345,0.9973858,0.001016801,0.001250894,0.0002560649,0.000003799152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03959329,0.0004918284,0.9550129,0.00037747,0.00005442422,0.00006872011,0.0001596729,0.002982962,0.001258713],"genre_scores_gemma":[0.5850254,0.0004081104,0.4077349,0.0005674181,0.00005587676,0.0004046032,0.001166002,0.0007107491,0.003926985],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004996781,"threshold_uncertainty_score":0.009935379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3453019355494129,"score_gpt":0.2655657906388144,"score_spread":0.07973614491059844,"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."}}