{"id":"W3020939278","doi":"10.1007/978-3-030-58598-3_35","title":"DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto; Université de Montréal","funders":"","keywords":"Discriminative model; Generalization; Computer science; Artificial intelligence; Metric (unit); Machine learning; Benchmark (surveying); Feature (linguistics); Similarity (geometry); Representation (politics); Feature learning; Class (philosophy); Aggregate (composite); Independent and identically distributed random variables; Range (aeronautics); Pattern recognition (psychology); Image (mathematics); 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":[0.001079132,0.001913525,0.002261023,0.001442707,0.0006551729,0.001476552,0.002773228,0.001415018,0.008909636],"category_scores_gemma":[0.003537084,0.0007465773,0.001153201,0.001824617,0.0005318832,0.0025093,0.003860071,0.002866521,0.00350262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00109412,"about_ca_system_score_gemma":0.001381636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005594667,"about_ca_topic_score_gemma":0.01106856,"domain_scores_codex":[0.9991482,0.000173238,0.00004399885,0.0002354946,0.0002987771,0.0001003371],"domain_scores_gemma":[0.9989738,0.0002158384,0.00004923171,0.0004347209,0.0002287223,0.00009770504],"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":[0.0004162585,0.0002511981,0.0009845418,0.0001998902,0.0001827061,0.0001055103,0.0000512526,0.05925259,0.009388997,0.01731589,0.06410056,0.8477507],"study_design_scores_gemma":[0.0000503071,0.000123166,0.0003515165,0.00001854387,0.00001879651,0.00007406424,0.00001907613,0.9511507,0.006205017,0.03400293,0.007965812,0.000020005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01305905,0.0006414401,0.9633452,0.0002512246,0.0002132138,0.0001306156,0.002275916,0.01815088,0.001932347],"genre_scores_gemma":[0.2471471,0.0004083987,0.7281502,0.0003959121,0.0001690122,0.0004900441,0.01115137,0.00221535,0.009872609],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008909636,"threshold_uncertainty_score":0.02980572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02367885656645275,"score_gpt":0.3189809680917443,"score_spread":0.2953021115252916,"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."}}