{"id":"W4312314147","doi":"10.1109/cvpr52688.2022.00071","title":"Frame Averaging for Equivariant Shape Space Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Equivariant map; Generalization; Computer science; Autoencoder; Artificial intelligence; Piecewise; Euclidean space; Homogeneous space; Algorithm; Mathematics; Theoretical computer science; Pattern recognition (psychology); Deep learning; Geometry; Pure mathematics; Mathematical analysis","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003377413,0.0002741779,0.0003375595,0.000260953,0.0004818984,0.0002427663,0.0001759682,0.00007339978,0.001873446],"category_scores_gemma":[0.000007363838,0.0002876352,0.0001438423,0.0001844614,0.00001994084,0.000127883,0.000106654,0.0005832078,0.00007996507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005324281,"about_ca_system_score_gemma":0.00001880225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572982,"about_ca_topic_score_gemma":0.00000422216,"domain_scores_codex":[0.9984206,0.0001271533,0.0003211828,0.0004739162,0.0003142683,0.0003428621],"domain_scores_gemma":[0.9993635,0.0001544651,0.00008221542,0.0001768678,0.00009076753,0.0001321728],"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":[0.00004326573,0.00007983448,0.0001686402,0.0001155445,0.0001041868,0.0000246334,0.0007717361,0.0962597,0.002052102,0.00004904468,0.00333094,0.8970004],"study_design_scores_gemma":[0.0006561435,0.0003618892,0.0000879569,0.0001260032,0.00003831362,0.00001822124,0.0001735658,0.9944009,0.0002397374,0.000617579,0.002889725,0.000390034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2396226,0.00006960086,0.7575001,0.0006050649,0.0008832186,0.0002275586,0.00009730898,0.0003489395,0.0006456298],"genre_scores_gemma":[0.9967026,0.0001529792,0.001399419,0.0008502345,0.0002609954,0.00009540536,0.0002620195,0.00005130368,0.0002251173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8981411,"threshold_uncertainty_score":0.9999576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.037609731627951,"score_gpt":0.2529882157833095,"score_spread":0.2153784841553585,"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."}}