{"id":"W4399392634","doi":"10.1007/s13042-024-02232-1","title":"Different gaze direction (DGNet) collaborative learning for iris segmentation","year":2024,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"IRIS (biosensor); Gaze; Artificial intelligence; Computer science; Computational intelligence; Segmentation; Computer vision; Pattern recognition (psychology); Biometrics","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":[0.0004402525,0.00009133906,0.0001139817,0.0003922031,0.0000901885,0.0005499995,0.0002244646,0.00004459894,0.00001997721],"category_scores_gemma":[0.0002520045,0.00007619247,0.00006947332,0.0002804861,0.00002472844,0.0002468887,0.00005521846,0.0003129081,0.000004007884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007791518,"about_ca_system_score_gemma":0.00004318234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000125516,"about_ca_topic_score_gemma":0.000004085275,"domain_scores_codex":[0.9989681,0.0001127636,0.0003018467,0.0001529402,0.0003761476,0.0000882089],"domain_scores_gemma":[0.9989435,0.0002835121,0.0002110415,0.00003929427,0.0004651429,0.00005747532],"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":[0.00008955641,0.0001477762,0.01170591,0.00005889219,0.000419695,0.00003589285,0.00556436,0.002244882,0.007112565,0.01952293,0.001990116,0.9511074],"study_design_scores_gemma":[0.0009547075,0.000549558,0.009781924,0.0001523446,0.0000516566,0.0002021856,0.0003315955,0.5646303,0.002610752,0.002384816,0.4181316,0.0002184656],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1031295,0.006245587,0.8840841,0.003394167,0.002507959,0.0001142382,0.000006790518,0.00008608563,0.0004315898],"genre_scores_gemma":[0.988097,0.001629489,0.007990823,0.00004660325,0.0002483687,0.000003766459,0.00001730287,0.000008702882,0.001957963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9508889,"threshold_uncertainty_score":0.5303658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01008029519878275,"score_gpt":0.2948244639995781,"score_spread":0.2847441688007954,"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."}}