{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001722347,0.0002334678,0.0002547686,0.00008539269,0.0003956274,0.001028014,0.0008661251,0.0000752126,0.00001740755],"category_scores_gemma":[0.00007969204,0.0001689081,0.00003634485,0.0008857273,0.0001508686,0.002017204,0.0004236406,0.0001312571,0.000007770665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002241037,"about_ca_system_score_gemma":0.00006472722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003588569,"about_ca_topic_score_gemma":0.00002180556,"domain_scores_codex":[0.9983419,0.0001064798,0.0002081895,0.0005834216,0.0003050099,0.000455038],"domain_scores_gemma":[0.9989738,0.0001628324,0.0002114606,0.0003617982,0.000204694,0.00008540587],"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":[0.0001603206,0.0001512665,0.0293104,0.0003489486,0.0007697569,0.002891258,0.0229332,0.0132684,0.01889545,0.02504574,0.02769967,0.8585256],"study_design_scores_gemma":[0.004766876,0.00107907,0.0192527,0.001844265,0.0002007593,0.0006224826,0.00330332,0.3825185,0.5364564,0.02809839,0.01830639,0.003550817],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4462034,0.001314512,0.5465758,0.002345956,0.001046234,0.001165378,0.00001634008,0.0006220567,0.0007102951],"genre_scores_gemma":[0.9867091,0.00001859556,0.01237672,0.0004035843,0.0003397925,0.00005746089,0.000004257305,0.00002150735,0.00006899858],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8549748,"threshold_uncertainty_score":0.9913159,"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."}}