{"id":"W4407276400","doi":"10.1061/jccee5.cpeng-6198","title":"Few-Shot Learning Augmented with Image Transformation for Multiclass Structural Damage Classification","year":2025,"lang":"en","type":"article","venue":"Journal of Computing in Civil Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Artificial intelligence; Transformation (genetics); Computer science; Computer vision; Shot (pellet); Image (mathematics); Pattern recognition (psychology); Multiclass classification; Class (philosophy); One shot; Machine learning; Engineering; Support vector machine; Materials science","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":[],"consensus_categories":[],"category_scores_codex":[0.0003128876,0.0001635024,0.000243062,0.0003680639,0.00005874715,0.00006227592,0.0001331003,0.00006433766,0.000001143373],"category_scores_gemma":[0.00007060171,0.0001473619,0.00006538942,0.0002837042,0.00001203475,0.0003023914,0.000009538452,0.0004528773,1.648641e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002276676,"about_ca_system_score_gemma":0.00002730384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001777717,"about_ca_topic_score_gemma":0.000009572232,"domain_scores_codex":[0.9990113,0.00001080158,0.0004887838,0.00008503859,0.0001383877,0.0002656896],"domain_scores_gemma":[0.9995189,0.0001244286,0.000107332,0.00007458141,0.000137752,0.00003703568],"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":[0.00002772153,0.00000357696,0.001272109,0.0002704367,0.00004505377,0.000004345548,0.0007147691,0.9474593,0.04755655,0.0002869001,0.00002159492,0.002337615],"study_design_scores_gemma":[0.001149242,0.00005231315,0.03470905,0.0007011534,0.0000234393,0.00001962875,0.0003623726,0.9541983,0.008095035,0.00002780538,0.0005148881,0.000146779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5292957,0.0000451525,0.4695603,0.00002894489,0.0004926012,0.0001097245,6.080292e-7,0.00006505689,0.0004019348],"genre_scores_gemma":[0.9827076,0.00000909269,0.01709263,0.000005773033,0.0001453589,0.00000310852,0.000003327947,0.00002599912,0.000007131202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4534119,"threshold_uncertainty_score":0.6009243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006316454175075249,"score_gpt":0.2385520859830618,"score_spread":0.2322356318079866,"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."}}