{"id":"W4390873396","doi":"10.1109/iccv51070.2023.01512","title":"Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Manitoba","funders":"","keywords":"Computer science; Generalization; Adaptation (eye); Inference; Artificial intelligence; Task (project management); Machine learning; Point cloud; Point (geometry); Test (biology); Multi-task learning; Time point","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":[0.002827143,0.002258522,0.002416282,0.001040288,0.0007561449,0.00137001,0.006207339,0.002424876,0.003255778],"category_scores_gemma":[0.008312276,0.001173928,0.002537028,0.001264618,0.001357538,0.003043255,0.00438478,0.004433492,0.002564419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009204816,"about_ca_system_score_gemma":0.001847532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006437566,"about_ca_topic_score_gemma":0.007393755,"domain_scores_codex":[0.9979954,0.0005235493,0.00009466633,0.0007974772,0.0003825521,0.0002063027],"domain_scores_gemma":[0.9963837,0.001041235,0.0003027279,0.001414148,0.0005597422,0.0002984355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006289191,0.0006703692,0.005242905,0.0001862202,0.0003860117,0.0002743115,0.00021145,0.4930205,0.02219221,0.003337627,0.01113599,0.4627135],"study_design_scores_gemma":[0.00001417801,0.00008141171,0.0004233861,0.000004922633,0.00001576992,0.00004557129,0.000009537687,0.9941307,0.002509314,0.001999447,0.0007493196,0.00001646824],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01862982,0.0002813594,0.9708623,0.0001584031,0.0001160911,0.0001122939,0.0002264597,0.008894399,0.0007187368],"genre_scores_gemma":[0.5742554,0.0002655666,0.4141129,0.0007296411,0.0002619403,0.0006847506,0.003171236,0.001875445,0.004643159],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006437566,"threshold_uncertainty_score":0.01495153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.108123742140849,"score_gpt":0.2703959946689375,"score_spread":0.1622722525280885,"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."}}