{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008567578,0.0004974255,0.0005515264,0.0009135976,0.0004339152,0.0009812715,0.003472765,0.0003601263,0.000002005839],"category_scores_gemma":[0.001685154,0.0004636102,0.0002127085,0.00387331,0.0002801891,0.001050569,0.005000572,0.001593109,0.000007410457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003456109,"about_ca_system_score_gemma":0.0003840537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002019872,"about_ca_topic_score_gemma":0.000009983619,"domain_scores_codex":[0.9959311,0.0001181247,0.0003920422,0.001961004,0.000872727,0.0007250219],"domain_scores_gemma":[0.9974226,0.0007451761,0.0003909655,0.0008011974,0.000437393,0.0002026677],"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":[0.00001257176,0.00003414636,0.0003759855,0.00009043766,0.000008447383,0.00002863677,0.0007457091,0.07336474,0.0005569456,0.0002415168,0.00002408129,0.9245168],"study_design_scores_gemma":[0.0002577677,0.0003285955,0.000480589,0.0001727411,0.000009568296,0.00001194102,0.000001110616,0.8916888,0.04703868,0.05908779,0.0003845477,0.00053789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006290996,0.0009014328,0.9935287,0.001910913,0.001461913,0.0009024627,0.000003633788,0.0006524327,0.000009466788],"genre_scores_gemma":[0.4389567,0.0000630369,0.5598229,0.000752394,0.0003397281,0.00003711864,0.00001044104,0.00001614048,0.000001575996],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9239789,"threshold_uncertainty_score":0.9997815,"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."}}