{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068951,0.0003197333,0.0002910176,0.0003618762,0.0006981677,0.0008780108,0.0004464491,0.0001437761,0.00005347731],"category_scores_gemma":[0.00008550918,0.0003269225,0.0002276573,0.0006762426,0.0001164097,0.002361253,0.000005426521,0.0007089843,0.00006822419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002019236,"about_ca_system_score_gemma":0.0003600049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001344245,"about_ca_topic_score_gemma":0.000007040694,"domain_scores_codex":[0.9977748,0.0001038954,0.0004356632,0.0008244068,0.0003310783,0.0005300876],"domain_scores_gemma":[0.9987661,0.0005178583,0.0001181699,0.0002565136,0.0002113088,0.0001300229],"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":[0.0001513217,0.00008325415,1.681648e-7,0.0002320447,0.0000728093,0.00003880772,0.005841862,0.04756144,0.003334751,0.0003795038,0.000165435,0.9421386],"study_design_scores_gemma":[0.001062,0.0001857082,0.00000254365,0.0005887641,0.0001058371,0.00008334063,0.0006965742,0.9804305,0.0112749,0.004566009,0.0005364876,0.0004673027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002513755,0.0001306814,0.9922507,0.00142348,0.00342002,0.0004888003,0.00003616796,0.001100412,0.0008983649],"genre_scores_gemma":[0.5910304,0.00000802723,0.4078267,0.0002117003,0.0005560003,0.0001378173,0.000007837406,0.00005825804,0.0001632742],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9416713,"threshold_uncertainty_score":0.9999183,"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."}}