{"id":"W3169447391","doi":"10.48550/arxiv.2106.06620","title":"Robust Representation Learning via Perceptual Similarity Metrics","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Overfitting; Computer science; Spurious relationship; Artificial intelligence; Metric (unit); Representation (politics); Machine learning; Feature learning; Similarity (geometry); Task (project management); Information bottleneck method; Bottleneck; Feature (linguistics); Generalization; Transformation (genetics); Mutual information; Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003685784,0.001234534,0.001090787,0.001167695,0.0004473513,0.001396271,0.001920968,0.001467087,0.001708211],"category_scores_gemma":[0.01177639,0.0005701888,0.0009711611,0.0008273775,0.002033078,0.002830997,0.003453294,0.003109492,0.0005579648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200215,"about_ca_system_score_gemma":0.0008683412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00139013,"about_ca_topic_score_gemma":0.001216218,"domain_scores_codex":[0.998178,0.0007107945,0.00007539011,0.0005178215,0.0004095896,0.0001084111],"domain_scores_gemma":[0.9966916,0.001709131,0.0003988686,0.0007618209,0.0003044702,0.0001340448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002011396,0.0001426086,0.001695131,0.0001562841,0.0001321631,0.00009970195,0.0001629686,0.7035592,0.01632863,0.06766896,0.003237449,0.2066157],"study_design_scores_gemma":[0.000007625221,0.00005020126,0.0001574079,0.000007658556,0.000006347882,0.00002433216,0.000007600239,0.9731807,0.00245734,0.02372081,0.000372541,0.000007377118],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0162527,0.0001863348,0.9817039,0.0002502192,0.00001731622,0.00003664149,0.00005741122,0.0005281054,0.0009672533],"genre_scores_gemma":[0.6952739,0.0003596158,0.2996379,0.0003593585,0.00008695008,0.0002054346,0.0005919066,0.0003864627,0.003098396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003685784,"threshold_uncertainty_score":0.01949257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1312729489414823,"score_gpt":0.2003486580711475,"score_spread":0.06907570912966518,"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."}}