{"id":"W4312300771","doi":"10.23919/eusipco55093.2022.9909919","title":"Boundary Enhanced Semantic Segmentation for High Resolution Electron Microscope Images","year":2022,"lang":"en","type":"article","venue":"2022 30th European Signal Processing Conference (EUSIPCO)","topic":"Integrated Circuits and Semiconductor Failure Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Infineon Technologies (Canada)","funders":"","keywords":"Computer science; Segmentation; Leverage (statistics); Artificial intelligence; Encoder; Image segmentation; Computer vision; Artificial neural network; Boundary (topology); Domain (mathematical analysis); Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004125341,0.0007333555,0.0005484554,0.001389683,0.0004294794,0.0009138284,0.001110623,0.00129394,0.002674269],"category_scores_gemma":[0.001080535,0.0003874198,0.0006693623,0.0006003973,0.0006238124,0.00158726,0.0007960265,0.00068449,0.001082806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007923417,"about_ca_system_score_gemma":0.000689311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002753944,"about_ca_topic_score_gemma":0.005417298,"domain_scores_codex":[0.9997619,0.00002492651,0.00001083045,0.00008431323,0.00007676009,0.00004132572],"domain_scores_gemma":[0.9996763,0.00008032286,0.00005528201,0.0000763785,0.00009372201,0.00001805737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006247018,0.0001758873,0.002201219,0.000316431,0.0001027059,0.0004798886,0.0003098231,0.1224424,0.2592088,0.0121399,0.004597014,0.5974011],"study_design_scores_gemma":[0.00001263945,0.00008732378,0.002093493,0.00003253006,0.00003435404,0.0002879802,0.00007895625,0.865813,0.1162659,0.0102285,0.005042907,0.00002251257],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07900691,0.0005198792,0.9112136,0.000205416,0.0000591711,0.0001010771,0.0003085969,0.004593518,0.003991877],"genre_scores_gemma":[0.4862524,0.00045726,0.5061814,0.0001809311,0.00004062629,0.00008222466,0.001206643,0.0003669563,0.005231552],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002753944,"threshold_uncertainty_score":0.008946359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01209613445298991,"score_gpt":0.2290229453689072,"score_spread":0.2169268109159173,"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."}}