{"id":"W2511989316","doi":"10.1109/access.2016.2603976","title":"Deep Randomly-Connected Conditional Random Fields For Image Segmentation","year":2016,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Ontario Ministry of Economic Development and Innovation","keywords":"Conditional random field; Random field; Computer science; Inference; Markov random field; Segmentation; Image segmentation; Artificial intelligence; Random graph; Prior probability; Maximum a posteriori estimation; Markov chain; Range (aeronautics); Pattern recognition (psychology); Theoretical computer science; Graph; Machine learning; Mathematics; Bayesian probability","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000192346,0.0001146848,0.0001621963,0.00007898026,0.0001149383,0.0001797412,0.0006615703,0.00005775887,0.0000617233],"category_scores_gemma":[0.0002173387,0.00007792829,0.00008820585,0.0001734287,0.00004682599,0.002449259,0.00006911885,0.00004618039,0.00001844952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003161031,"about_ca_system_score_gemma":0.00002849636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003871178,"about_ca_topic_score_gemma":0.00000371422,"domain_scores_codex":[0.9990771,0.00004297066,0.0002160441,0.0002896748,0.0001655405,0.0002086251],"domain_scores_gemma":[0.9986296,0.0007412907,0.0001070157,0.0002599037,0.0002065871,0.0000555968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001675299,0.0002170154,0.0003945753,0.0001057596,0.0001348361,0.00004996669,0.0003206336,0.00005546276,0.326923,0.02234088,0.04888088,0.5989017],"study_design_scores_gemma":[0.007595605,0.00008719555,0.0002097676,0.00002575075,0.000009592629,0.000009172129,0.000002719365,0.002457771,0.8686621,0.1188162,0.001927798,0.0001963723],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002066268,0.00004381268,0.9952959,0.001173776,0.0002900781,0.0005439503,0.00001340276,0.0002819206,0.0002909126],"genre_scores_gemma":[0.889328,0.00009155999,0.1080527,0.001350383,0.0002723767,0.000400555,0.00002073473,0.00001709368,0.0004666252],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8872617,"threshold_uncertainty_score":0.3177823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02405195770782983,"score_gpt":0.3399639052669103,"score_spread":0.3159119475590805,"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."}}