{"id":"W3149955010","doi":"10.48550/arxiv.2103.14953","title":"OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Novelty; Computer science; Novelty detection; Context (archaeology); Artificial intelligence; Masking (illustration); Pattern recognition (psychology); MNIST database; Autoencoder; Encoder; Computer vision; Deep learning","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":[0.0005336109,0.001190409,0.0008097755,0.0003323779,0.0003055589,0.0005223274,0.001857528,0.001281191,0.002671364],"category_scores_gemma":[0.001051333,0.0004529009,0.0005869349,0.0002182456,0.0006516277,0.0009770795,0.001411126,0.001552879,0.000803392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007540054,"about_ca_system_score_gemma":0.0008590729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003457254,"about_ca_topic_score_gemma":0.005523277,"domain_scores_codex":[0.999745,0.00004589106,0.00001022473,0.00007773518,0.0000752572,0.00004592482],"domain_scores_gemma":[0.9997414,0.00009261396,0.00002749254,0.00005694034,0.00005387421,0.00002765358],"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":[0.0005022637,0.0002634235,0.001357267,0.0001833774,0.000182953,0.0004482181,0.00009441189,0.6048952,0.02941843,0.01351518,0.009250426,0.3398888],"study_design_scores_gemma":[0.00001249533,0.00005804965,0.00007953136,0.000005961281,0.00001165803,0.00005600295,0.000003444132,0.9931814,0.003697878,0.002129076,0.0007568309,0.000007603834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03848764,0.001408435,0.9488241,0.0004921286,0.0002167253,0.000122969,0.0002912417,0.004658058,0.00549869],"genre_scores_gemma":[0.7948219,0.0005580705,0.1885496,0.0007106055,0.00009622233,0.0002074535,0.0008178087,0.0001930026,0.01404518],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003457254,"threshold_uncertainty_score":0.008936584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08390783299909817,"score_gpt":0.1988152913939423,"score_spread":0.1149074583948441,"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."}}