{"id":"W3033437302","doi":"10.1007/978-3-030-58526-6_37","title":"Info3D: Representation Learning on 3D Objects Using Mutual Information Maximization and Contrastive Learning","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Autodesk (Canada)","funders":"","keywords":"Infomax; Mutual information; Computer science; Artificial intelligence; Maximization; Feature learning; Representation (politics); Cluster analysis; Unsupervised learning; Pattern recognition (psychology); Machine learning; Mathematics; Channel (broadcasting)","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":[0.0002928913,0.0002254945,0.0002678051,0.0004867614,0.0001778363,0.0004105845,0.000195894,0.0001549698,0.000002518677],"category_scores_gemma":[0.0004722235,0.0002357428,0.00004010764,0.0007251448,0.00008467617,0.0004427021,0.0002606557,0.0009978792,0.000004483676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000162854,"about_ca_system_score_gemma":0.00007803604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005129695,"about_ca_topic_score_gemma":0.000008654421,"domain_scores_codex":[0.9986343,0.00006341567,0.000317599,0.0003782454,0.0003652841,0.000241089],"domain_scores_gemma":[0.9993666,0.0001703749,0.0001308848,0.0001461558,0.000116949,0.00006899851],"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":[0.00000533402,0.000002281503,0.0009567447,0.00005263038,0.00001012564,0.000001972262,0.004214435,0.8768591,0.000293837,0.00000194071,3.649543e-7,0.1176012],"study_design_scores_gemma":[0.0001583821,0.00003934127,0.0005252106,0.0002190833,0.00001676054,0.000003468574,0.00001314676,0.9970626,0.001329648,0.0004022883,0.000002746201,0.0002273206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1652285,0.00005007027,0.8340322,0.00005090321,0.0002954817,0.0001258952,0.000001289978,0.0001845542,0.00003117691],"genre_scores_gemma":[0.9493883,0.0000381454,0.05026462,0.0001074807,0.000144664,0.000004426682,0.00003871646,0.00001336221,2.313635e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7841599,"threshold_uncertainty_score":0.9613314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01723232900074114,"score_gpt":0.2470134514731537,"score_spread":0.2297811224724126,"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."}}