{"id":"W4293863504","doi":"10.1109/siu55565.2022.9864873","title":"Semantic Segmentation with the Mixup Data Augmentation Method","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Image segmentation; Computer vision; Natural language processing","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009638165,0.000171661,0.0001520444,0.0001448452,0.003428409,0.0005447028,0.004850241,0.00002675415,0.00004496382],"category_scores_gemma":[0.000009375362,0.0001427532,0.0000185498,0.001331963,0.0002638592,0.0008209446,0.003787952,0.000548635,0.000008424166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001012864,"about_ca_system_score_gemma":0.0003837196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007427583,"about_ca_topic_score_gemma":0.00004466577,"domain_scores_codex":[0.9977662,0.0004738153,0.0002862904,0.0006247203,0.0005797268,0.0002692765],"domain_scores_gemma":[0.9960908,0.0003694482,0.0002595397,0.002942754,0.0002541947,0.00008328963],"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":[0.00001209682,0.000153748,0.00005136634,0.00003958362,0.00003106341,8.212854e-7,0.001934259,0.001683271,0.002417291,0.01829992,0.0003056102,0.975071],"study_design_scores_gemma":[0.0003590435,0.00008852888,0.0001678482,0.00001773176,0.00003649028,0.00006377462,0.004705007,0.9631143,0.0002324683,0.004012355,0.02696001,0.0002424798],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002334729,0.001137268,0.9859623,0.01107598,0.00001037497,0.0007624336,0.00004493135,0.0001607696,0.0006124306],"genre_scores_gemma":[0.5893971,0.000206605,0.4060856,0.0003630522,0.00002300777,0.002996346,0.0003883729,0.00002124904,0.0005186494],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9748285,"threshold_uncertainty_score":0.997869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07743756159890856,"score_gpt":0.371879965193126,"score_spread":0.2944424035942175,"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."}}