{"id":"W2950911758","doi":"10.48550/arxiv.1807.06072","title":"Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Minimum bounding box; Computer science; Annotation; Artificial intelligence; Task (project management); Segmentation; Object (grammar); Object detection; Bounding overwatch; Ground truth; Scheme (mathematics); Point cloud; Orientation (vector space); Generalization; Point (geometry); Computer vision; Machine learning; Image (mathematics)","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":[0.001369048,0.00271339,0.001263811,0.001784458,0.0006920488,0.001782913,0.004046167,0.002286363,0.005143516],"category_scores_gemma":[0.004148846,0.001756729,0.001397989,0.001390153,0.0009953555,0.002431717,0.002628666,0.002846022,0.006274967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001693631,"about_ca_system_score_gemma":0.001714598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01334791,"about_ca_topic_score_gemma":0.03210216,"domain_scores_codex":[0.9987412,0.0001133523,0.00003691083,0.0006700816,0.000330064,0.00010847],"domain_scores_gemma":[0.9978689,0.0005622312,0.0001503089,0.000817332,0.0005262771,0.00007485132],"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":[0.000246366,0.0003069395,0.004517262,0.0002767697,0.0001779748,0.0002273126,0.0001750135,0.216907,0.04973062,0.002980763,0.02338866,0.7010653],"study_design_scores_gemma":[0.00001200942,0.00005993621,0.001196461,0.00002805173,0.00001798822,0.00008511726,0.00003535879,0.9655018,0.02484903,0.003269293,0.004921387,0.00002350603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02710392,0.0002932994,0.9347024,0.0001913098,0.0001543615,0.0001822941,0.001507487,0.03321639,0.002648592],"genre_scores_gemma":[0.296172,0.0003818403,0.6842235,0.0003628471,0.0000593582,0.0003252361,0.01054871,0.001908674,0.006017813],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01334791,"threshold_uncertainty_score":0.02654046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1093163545601712,"score_gpt":0.217894364831059,"score_spread":0.1085780102708878,"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."}}