{"id":"W4313591763","doi":"10.1109/access.2022.3233874","title":"Progressive With Purpose: Guiding Progressive Inpainting DNNs Through Context and Structure","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Inpainting; Artificial intelligence; Computer science; Deep learning; Benchmarking; Context (archaeology); Feature (linguistics); Pattern recognition (psychology); Image (mathematics); Convolutional neural network; Feature extraction; Encoder; Pyramid (geometry); Feature learning; Computer vision; 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":[0.0003600411,0.0007502604,0.0004075308,0.0002685492,0.000187181,0.000367707,0.001027209,0.0005312552,0.001586032],"category_scores_gemma":[0.000877266,0.0002828969,0.000305776,0.0001721334,0.0004754037,0.0006040317,0.0008163455,0.0009328933,0.0002505087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004604845,"about_ca_system_score_gemma":0.0004948949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002450498,"about_ca_topic_score_gemma":0.006745006,"domain_scores_codex":[0.9998989,0.00001556651,0.000004178452,0.00003284956,0.00002878906,0.00001964352],"domain_scores_gemma":[0.9998353,0.00006785996,0.00002215875,0.00002949982,0.00002943499,0.00001570871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000285834,0.0001557266,0.001308698,0.0001728592,0.00006976935,0.0003159404,0.000216675,0.6130297,0.07229473,0.01101898,0.003772915,0.2973583],"study_design_scores_gemma":[0.00001547029,0.00006337723,0.0001850381,0.00001246913,0.00001636971,0.00007659764,0.00001311022,0.9827852,0.01178288,0.003620612,0.001423524,0.000005381841],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0587764,0.0007836651,0.9354269,0.000168421,0.00008432521,0.00007438168,0.00008522731,0.001232851,0.003367857],"genre_scores_gemma":[0.7690795,0.0005362011,0.2253254,0.0003095673,0.00005465283,0.00006814328,0.0001940903,0.0001361827,0.004296221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002450498,"threshold_uncertainty_score":0.005305767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03939070831493946,"score_gpt":0.2947518605369867,"score_spread":0.2553611522220472,"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."}}