{"id":"W2907097116","doi":"10.48550/arxiv.1901.00212","title":"EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":587,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Inpainting; Hallucinating; Generator (circuit theory); Image (mathematics); Enhanced Data Rates for GSM Evolution; Artificial intelligence; Computer science; Filling-in; Code (set theory); A priori and a posteriori; Generative grammar; Deep learning; Pattern recognition (psychology); Computer vision; Power (physics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005120975,0.0006166423,0.0006646717,0.0002920062,0.0004486892,0.0004690236,0.001789617,0.0003525017,0.00008822911],"category_scores_gemma":[0.0001312806,0.0006206739,0.0002985712,0.0006595736,0.0001944305,0.00102677,0.002476333,0.001267851,0.0002265182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002631923,"about_ca_system_score_gemma":0.0003970233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001805678,"about_ca_topic_score_gemma":0.0000652939,"domain_scores_codex":[0.9964255,0.0005778949,0.0002912893,0.001868178,0.0001632065,0.0006739002],"domain_scores_gemma":[0.9973087,0.0002934178,0.000522075,0.001224012,0.000442748,0.000209046],"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":[0.00006371713,0.00005812526,0.001294312,0.00004675979,0.0002491661,0.0002484549,0.0006291782,0.9826382,0.0002991389,0.01264201,0.0005907513,0.0012402],"study_design_scores_gemma":[0.000979315,0.0001803665,0.0003586284,0.0001434512,0.0001141822,0.000006534929,0.0002510404,0.9916211,0.0015322,0.002477336,0.001429219,0.0009066237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04190781,0.00006148791,0.9467519,0.0001574659,0.001234576,0.0004909754,0.000008787009,0.0002890531,0.009097962],"genre_scores_gemma":[0.9732144,0.00007289344,0.02291158,0.0001347928,0.0006071913,0.00000231375,0.00002803786,0.00004739963,0.002981401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9313066,"threshold_uncertainty_score":0.9996244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03475309409311431,"score_gpt":0.1705201107510971,"score_spread":0.1357670166579828,"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."}}