{"id":"W3195393125","doi":"10.1007/s11263-022-01720-7","title":"SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; York University; Toronto Metropolitan University; Vector Institute","funders":"","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Categorical variable; Pooling; Segmentation; Convolutional neural network; Boosting (machine learning); Adversarial system; Cluster analysis; Object detection; Salient; Machine learning","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":[0.0007543598,0.0001440352,0.0002147002,0.0003523507,0.0002557831,0.0002476051,0.001343617,0.00003405603,0.00002832501],"category_scores_gemma":[0.0000557512,0.0001427676,0.000123257,0.0001457134,0.00003954556,0.0009559277,0.0006999705,0.000325718,0.000001384629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001720342,"about_ca_system_score_gemma":0.0001158126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003709883,"about_ca_topic_score_gemma":5.414782e-7,"domain_scores_codex":[0.9979306,0.0001965613,0.0005025244,0.0002702607,0.0009320091,0.0001680138],"domain_scores_gemma":[0.9983601,0.0003665458,0.0006311677,0.0001503755,0.0004094742,0.00008234546],"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":[0.0003157923,0.0001596477,0.001371401,0.00001757404,0.0001426422,0.0001318254,0.001118982,0.8464434,0.0008632559,0.003270749,0.00433443,0.1418304],"study_design_scores_gemma":[0.002370379,0.0006778041,0.001268675,0.00005149517,0.00001845099,0.0005959103,0.00006175686,0.9883383,0.0001756409,0.0008411175,0.005421818,0.0001786371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05893806,0.00003842549,0.9338856,0.001544457,0.005366408,0.0001602608,0.00002172646,0.00002894173,0.00001609194],"genre_scores_gemma":[0.7719517,0.00001307923,0.2269288,0.0002714401,0.0007667047,0.000007413576,0.00003463259,0.000009868971,0.00001632365],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7130136,"threshold_uncertainty_score":0.5821894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01239074950144367,"score_gpt":0.3148305969806831,"score_spread":0.3024398474792395,"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."}}