{"id":"W4392543429","doi":"10.1109/tip.2024.3372456","title":"PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Point cloud; Computer science; Adversarial system; Robustness (evolution); Artificial intelligence; Boosting (machine learning); Leverage (statistics); Pattern recognition (psychology); 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":[0.001464378,0.001281841,0.0009257262,0.0004815483,0.0003442012,0.0006581076,0.001932391,0.001315199,0.003582845],"category_scores_gemma":[0.004629213,0.0004769092,0.0008076652,0.0004332648,0.001330543,0.001023456,0.002618014,0.002798442,0.001159654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007525331,"about_ca_system_score_gemma":0.0008693116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002416462,"about_ca_topic_score_gemma":0.002650198,"domain_scores_codex":[0.999184,0.0002448359,0.00003280761,0.0001958218,0.0002557669,0.00008689624],"domain_scores_gemma":[0.9985631,0.0008084666,0.0001199233,0.0002930422,0.0001515482,0.0000640147],"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":[0.0001269377,0.00005254749,0.0006282598,0.00007658919,0.00006476453,0.00009054351,0.00003733353,0.897871,0.006103082,0.01567436,0.005014641,0.07425998],"study_design_scores_gemma":[0.000004479972,0.0000163915,0.00004578069,0.000004389905,0.000002433699,0.00001879024,0.000002021675,0.9947833,0.001207716,0.003380112,0.0005304752,0.000004013164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004739988,0.0001293806,0.9921898,0.000137223,0.00004289199,0.00005611364,0.00009628139,0.001479202,0.001129056],"genre_scores_gemma":[0.5509699,0.0003302116,0.4392015,0.0007245677,0.000108278,0.0004692725,0.001031822,0.0007320995,0.006432318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003582845,"threshold_uncertainty_score":0.01198578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03959340633078498,"score_gpt":0.2901404290749319,"score_spread":0.250547022744147,"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."}}