{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003183873,0.0001135556,0.0001425024,0.000259541,0.0002396096,0.00002806177,0.00009415248,0.0000190642,0.00004715591],"category_scores_gemma":[0.000001908064,0.0001116553,0.00005935196,0.0003200088,0.0000557537,0.0002745307,0.000002862253,0.00009645039,6.400948e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003304184,"about_ca_system_score_gemma":0.00007488222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005728278,"about_ca_topic_score_gemma":0.0001606722,"domain_scores_codex":[0.9987191,0.00007771726,0.0002818707,0.000293295,0.0004841307,0.000143866],"domain_scores_gemma":[0.999534,0.00002355851,0.0001415675,0.0001206857,0.0001291705,0.00005104624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007118491,0.001292705,0.0002813775,0.00007542541,0.0002752809,0.00000215242,0.004197177,0.3741812,0.0143527,0.001793407,0.00003220468,0.6028045],"study_design_scores_gemma":[0.009639828,0.001893206,0.001004476,0.0001427447,0.000148618,0.00007187931,0.0137692,0.8544733,0.1177028,0.0004475683,0.0002201569,0.0004862786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01128652,0.0000238678,0.9873019,0.0005366757,0.0001841123,0.0005237052,0.00006120529,0.00002916564,0.00005279863],"genre_scores_gemma":[0.9676423,0.00002994721,0.03179952,0.0000889336,0.000004136421,0.000396065,0.000005283384,0.000006119139,0.00002765991],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9563558,"threshold_uncertainty_score":0.4553171,"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."}}