{"id":"W2802173845","doi":"10.1109/icassp.2018.8462057","title":"A Rotation-Invariant Convolutional Neural Network for Image Enhancement Forensics","year":2018,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Overfitting; Convolutional neural network; Computer science; Artificial intelligence; Robustness (evolution); Invariant (physics); Pattern recognition (psychology); Rotation (mathematics); Computer vision; Artificial neural network; 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":[0.0001959801,0.0001104238,0.0001024157,0.00003926389,0.0001497709,0.0001804871,0.0002798705,0.00003416594,0.00003538578],"category_scores_gemma":[0.00009357204,0.0000984879,0.00006096575,0.0002471699,0.000133309,0.0007004368,0.0001076565,0.00004127617,0.0001396382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005388685,"about_ca_system_score_gemma":0.00006935306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000011779,"about_ca_topic_score_gemma":0.00005370967,"domain_scores_codex":[0.9988958,0.00001476342,0.0002107168,0.0003058146,0.0002398336,0.0003330209],"domain_scores_gemma":[0.999116,0.0001230252,0.00007490467,0.0002805924,0.0003202099,0.00008524615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004454797,0.00004895685,0.00005225579,0.00001195953,0.00003605143,0.000003842353,0.0002247787,0.0001283173,0.001333305,0.7761331,0.07292482,0.1490581],"study_design_scores_gemma":[0.0007985875,0.0008873311,0.0006942769,0.00001692853,0.000009506085,0.00003289174,0.00002158574,0.8048071,0.01866902,0.160578,0.01319441,0.0002903375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004415651,0.000008418547,0.9836443,0.000968635,0.002702898,0.0003872721,0.000003678049,0.0001641922,0.007704928],"genre_scores_gemma":[0.4265385,6.395135e-7,0.5704231,0.001049963,0.0009708478,0.000109231,0.00001432374,0.000009245014,0.0008841702],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8046787,"threshold_uncertainty_score":0.401622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01451261910649984,"score_gpt":0.2429311390566931,"score_spread":0.2284185199501932,"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."}}