{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002781701,0.003016201,0.002601377,0.002165058,0.001085464,0.002471497,0.003884967,0.004535184,0.01004712],"category_scores_gemma":[0.006880502,0.001594298,0.002426926,0.001809847,0.001914326,0.00368039,0.008202261,0.00513069,0.005676272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001052846,"about_ca_system_score_gemma":0.00148569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00296228,"about_ca_topic_score_gemma":0.004991841,"domain_scores_codex":[0.997872,0.0004589634,0.00009799684,0.000678025,0.0006822078,0.0002107277],"domain_scores_gemma":[0.9981279,0.0008659945,0.0001254331,0.0005111105,0.0002514661,0.0001182334],"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":[0.00101736,0.0002752405,0.0007297493,0.0002715882,0.0004198026,0.00031777,0.0001727107,0.3298042,0.02912129,0.03047071,0.01457637,0.5928231],"study_design_scores_gemma":[0.00001464723,0.00004705279,0.00009212209,0.00001180134,0.00001800336,0.00007502719,0.00001585947,0.970727,0.009912302,0.01683876,0.002227318,0.00002010488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002840062,0.0001688735,0.990564,0.0001067417,0.00006458963,0.00007287692,0.0001826604,0.005379794,0.0006203701],"genre_scores_gemma":[0.135397,0.0002591855,0.8503991,0.0004805613,0.0001655964,0.0003892714,0.002024928,0.002738317,0.008145954],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01004712,"threshold_uncertainty_score":0.03361094,"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."}}