{"id":"W4223476417","doi":"10.1088/1361-6501/ac6663","title":"Lightweight edge-attention network for surface-defect detection of rubber seal rings","year":2022,"lang":"en","type":"article","venue":"Measurement Science and Technology","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"MD Precision (Canada)","funders":"","keywords":"Computer science; Pyramid (geometry); Backbone network; Artificial intelligence; Convolutional neural network; Block (permutation group theory); Edge detection; Bottleneck; Feature (linguistics); Artificial neural network; Enhanced Data Rates for GSM Evolution; Natural rubber; Pattern recognition (psychology); Computer vision; Algorithm; Image processing; Image (mathematics); Embedded system; Mathematics; Materials science; Computer network","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":[0.002512004,0.00009229299,0.0001542601,0.0003013979,0.0005276074,0.00002060466,0.0001362144,0.00007996459,0.000007477404],"category_scores_gemma":[0.00008592705,0.00008953315,0.00004301303,0.001369272,0.0001114597,0.0001063914,0.00006270798,0.0001582696,0.000001886741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002946061,"about_ca_system_score_gemma":0.00004071606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001453107,"about_ca_topic_score_gemma":0.00002196691,"domain_scores_codex":[0.9986074,0.00002075186,0.0002213075,0.0002239962,0.0006562292,0.0002703374],"domain_scores_gemma":[0.9993747,0.00001287342,0.00006878965,0.0001603581,0.0003521099,0.00003117281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002041701,0.00001626881,0.001514425,0.00003322489,0.0000202437,4.250214e-7,0.0000252163,0.002844476,0.9760446,0.0006951101,0.0005825109,0.01820306],"study_design_scores_gemma":[0.001419182,0.001206599,0.002589267,0.00005620115,0.00006203554,0.00004943677,0.00046119,0.01990939,0.8905815,0.001598072,0.08166402,0.0004031196],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890351,0.0004662949,0.007563132,0.0001078869,0.001563801,0.0005146162,0.000003808886,0.0002789598,0.0004663923],"genre_scores_gemma":[0.9996879,0.000007122395,0.0001203635,0.00000477635,0.00006331438,0.00008518283,4.301627e-7,0.00001038827,0.00002051066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08546313,"threshold_uncertainty_score":0.4057983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02131491604248945,"score_gpt":0.2145451222289261,"score_spread":0.1932302061864366,"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."}}