{"id":"W4389667410","doi":"10.1109/iros55552.2023.10341345","title":"Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Manitoba","funders":"","keywords":"Upsampling; Computer science; Point cloud; Cloud computing; Generality; Adaptation (eye); Artificial intelligence; Set (abstract data type); Test set; Test data; Point (geometry); Machine learning; Meta learning (computer science); Test (biology); Data mining; Image (mathematics); Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0003222729,0.0001083731,0.0002015971,0.0001428534,0.000109256,0.00004326296,0.00005397739,0.00004364454,0.0001055933],"category_scores_gemma":[0.0001404746,0.00009854481,0.0001867957,0.0002908678,0.00000445699,0.00007898609,0.00001409309,0.0000793161,0.0001319393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002599067,"about_ca_system_score_gemma":0.000006722827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002590249,"about_ca_topic_score_gemma":0.000003220599,"domain_scores_codex":[0.9993586,0.000009305568,0.0001857466,0.0001374885,0.00009864554,0.0002102484],"domain_scores_gemma":[0.9995692,0.0002368702,0.0000207475,0.00008880252,0.00004467969,0.00003968785],"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":[9.054352e-7,0.000001979273,0.000006428973,0.00002118077,0.0001739116,4.793154e-7,0.0001743206,0.9917943,0.006897375,0.00002957165,0.0001567996,0.0007427164],"study_design_scores_gemma":[0.00008449924,0.000009657525,0.00000303984,0.000007046191,0.0004179599,7.105522e-7,0.0002548652,0.9974682,0.001150518,0.0002624575,0.0002141583,0.0001269311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05024146,0.00006130533,0.9480119,0.00007345503,0.00007690536,0.00006887313,0.000005138748,0.001096318,0.0003646852],"genre_scores_gemma":[0.9425667,0.00001619742,0.05555199,0.0000275294,0.0001458914,0.00001778771,0.00003415414,0.0000473217,0.00159245],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8924599,"threshold_uncertainty_score":0.4018541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08583134544967143,"score_gpt":0.2664668660377022,"score_spread":0.1806355205880308,"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."}}