{"id":"W4226497253","doi":"10.1109/tim.2022.3165261","title":"A Deep Autoencoder With Novel Adaptive Resolution Reconstruction Loss for Disentanglement of Concepts in Face Images","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Face recognition and analysis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Autoencoder; Artificial intelligence; Face (sociological concept); Computer science; Benchmark (surveying); Iterative reconstruction; Pattern recognition (psychology); Computer vision; Representation (politics); Deep learning; Facial recognition system; Image (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":[0.0009406292,0.0009177628,0.0006257122,0.0003636144,0.0002025124,0.0005170822,0.000893943,0.0009296515,0.001139787],"category_scores_gemma":[0.001793674,0.0004097949,0.0006967796,0.0003039855,0.0005139874,0.001237588,0.0009821657,0.001918845,0.0004596414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004910114,"about_ca_system_score_gemma":0.0007396396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003833758,"about_ca_topic_score_gemma":0.004522866,"domain_scores_codex":[0.9996674,0.00007494376,0.00002042561,0.0000860471,0.000112379,0.00003887939],"domain_scores_gemma":[0.9996014,0.0001614379,0.0000400643,0.0000631413,0.0001111104,0.00002297518],"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":[0.0002108597,0.0001933555,0.001316487,0.0001122665,0.0001354844,0.0001560255,0.00009165786,0.6221176,0.04013211,0.01103164,0.003789558,0.320713],"study_design_scores_gemma":[0.000003096776,0.00002538786,0.00010666,0.000004347599,0.000007011816,0.00002323961,0.000002963016,0.996098,0.002674331,0.0007498561,0.0003011652,0.000003966776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02253334,0.0003719556,0.9750592,0.0001915028,0.00005774318,0.00003008709,0.00006616419,0.0005947938,0.001095268],"genre_scores_gemma":[0.5667335,0.0007662065,0.4223981,0.0004617528,0.00009441048,0.0001760909,0.0007146919,0.0001720398,0.008483257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003833758,"threshold_uncertainty_score":0.007622898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03825632709327617,"score_gpt":0.2627208004155365,"score_spread":0.2244644733222603,"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."}}