{"id":"W4283794091","doi":"10.1609/aaai.v36i1.19938","title":"PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; McGill University; Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Regularization (linguistics); Robustness (evolution); Pattern recognition (psychology); Feature vector; Generalization; Block (permutation group theory); Deep neural networks; Deep learning; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001210649,0.00098548,0.0008202153,0.0005504558,0.0004247034,0.0004056575,0.001422349,0.001057377,0.001912826],"category_scores_gemma":[0.002514719,0.0004269081,0.0007514596,0.0005359713,0.0007742115,0.001015253,0.001471205,0.002218072,0.0006364389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005715978,"about_ca_system_score_gemma":0.0009104711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003054779,"about_ca_topic_score_gemma":0.005257171,"domain_scores_codex":[0.9995541,0.0001336157,0.00002084632,0.00008515965,0.0001519976,0.000054228],"domain_scores_gemma":[0.999356,0.000196633,0.00007793501,0.0002166588,0.000111567,0.0000413346],"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":[0.0003512754,0.0002847025,0.002205917,0.000210545,0.0002741685,0.0001801334,0.0001934295,0.5061443,0.0636306,0.03548234,0.01533345,0.3757091],"study_design_scores_gemma":[0.00001492978,0.0000618517,0.0001988197,0.000007995526,0.00001210848,0.00004360913,0.000005719286,0.9856945,0.007993415,0.003920632,0.002037884,0.000008548451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0130054,0.0002251719,0.983698,0.0001391325,0.00003090016,0.00006710418,0.00009103445,0.00185437,0.0008890732],"genre_scores_gemma":[0.3632815,0.0003777012,0.6278802,0.0003911651,0.0000955737,0.0004215912,0.0008223343,0.000787145,0.005942731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003054779,"threshold_uncertainty_score":0.006402552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05613656257909424,"score_gpt":0.2852592275984625,"score_spread":0.2291226650193683,"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."}}