{"id":"W2902806643","doi":"10.48550/arxiv.1811.12608","title":"DeepFlux for Skeletons in the Wild","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Skeletonization; Artificial intelligence; Computer science; Computer vision; Pixel; Benchmark (surveying); Context (archaeology); Object detection; Segmentation; Pattern recognition (psychology); Object (grammar); Clutter; Point (geometry); Image segmentation; Representation (politics); Topological skeleton; Edge detection; Field (mathematics); Image (mathematics); Image processing; Mathematics; Geography; Cartography; Active shape model","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":[0.000606688,0.001928846,0.001197013,0.001497426,0.000655556,0.00151957,0.003154703,0.00165748,0.01184006],"category_scores_gemma":[0.001695995,0.0007339386,0.001143361,0.001033545,0.000761007,0.003436944,0.001751855,0.001982564,0.004185094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001485919,"about_ca_system_score_gemma":0.001203048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01295769,"about_ca_topic_score_gemma":0.02080845,"domain_scores_codex":[0.999678,0.00002449201,0.00001357023,0.0001464371,0.00007771383,0.0000597713],"domain_scores_gemma":[0.9996719,0.00006961318,0.00003439604,0.0001270286,0.00006844589,0.00002860965],"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":[0.0004017977,0.0002123188,0.002669511,0.0003148714,0.0001451923,0.0003324769,0.00009473667,0.1910218,0.01588019,0.02369244,0.06380543,0.7014291],"study_design_scores_gemma":[0.00002252484,0.00004550754,0.0004925816,0.00002547695,0.00001482738,0.00009167378,0.0000194252,0.9711712,0.004819441,0.0170535,0.00623475,0.000009001513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.07591575,0.002435604,0.8501493,0.001069362,0.0005096334,0.000199023,0.005683775,0.05262795,0.01140969],"genre_scores_gemma":[0.4299061,0.001248366,0.5230474,0.0007307534,0.0002101186,0.0003038659,0.01873426,0.002288882,0.02353025],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01295769,"threshold_uncertainty_score":0.0396089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08713992578444996,"score_gpt":0.219164297662599,"score_spread":0.132024371878149,"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."}}