{"id":"W3034455598","doi":"10.24963/ijcai.2020/285","title":"Compressed Self-Attention for Deep Metric Learning with Low-Rank Approximation","year":2020,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Wuhan University; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Hubei Province; National Natural Science Foundation of China","keywords":"Metric (unit); Computer science; Pooling; Landmark; Artificial intelligence; Feature (linguistics); Pairwise comparison; Rank (graph theory); Deep learning; Pattern recognition (psychology); Computation; Similarity (geometry); Task (project management); Machine learning; Algorithm; Mathematics; Image (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":[0.0004133115,0.0001010105,0.0001520601,0.00008176484,0.0001283178,0.0001587298,0.0002986167,0.00003661241,0.00000584707],"category_scores_gemma":[0.00009708466,0.00007990689,0.00005255615,0.0007616485,0.000008742323,0.000422278,0.00004807353,0.00009790326,0.00001934691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001411115,"about_ca_system_score_gemma":0.00002101436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004910019,"about_ca_topic_score_gemma":0.000002454561,"domain_scores_codex":[0.9990229,0.0001167728,0.0001564061,0.000319105,0.0002019252,0.0001828718],"domain_scores_gemma":[0.9993274,0.000226068,0.00009313381,0.000161937,0.0001220736,0.00006945285],"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":[0.0002686907,0.000535327,0.05551454,0.001340965,0.0004566071,0.00002352254,0.006254743,0.07894803,0.01494319,0.08138858,0.0009244803,0.7594013],"study_design_scores_gemma":[0.0008085793,0.0002322373,0.00831989,0.00001002611,0.00001074222,0.000002917906,0.00003646046,0.9859151,0.002890037,0.0003541647,0.001259405,0.0001603875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008663587,0.00004281345,0.9883953,0.001031217,0.00006958115,0.0002743429,2.436844e-7,0.0005589842,0.0009639767],"genre_scores_gemma":[0.5551813,0.000003016851,0.4444512,0.0002714378,0.00004021626,0.00001943594,0.000004661445,0.000006674321,0.0000221419],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9069671,"threshold_uncertainty_score":0.3258509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02014887226945844,"score_gpt":0.2600178486111484,"score_spread":0.2398689763416899,"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."}}