{"id":"W4287367114","doi":"10.1109/tpami.2022.3218591","title":"Deep Learning for Instance Retrieval: A Survey","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"China Scholarship Council; Academy of Finland; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Image retrieval; Artificial intelligence; Feature extraction; Content-based image retrieval; Feature (linguistics); Process (computing); Machine learning; Information retrieval; Embedding; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001860848,0.001632261,0.002377674,0.002320335,0.0003643861,0.002406375,0.002633322,0.001640379,0.005509849],"category_scores_gemma":[0.005781345,0.0006538501,0.001147839,0.003842139,0.0005392488,0.004083376,0.001603505,0.002230127,0.002682624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001121765,"about_ca_system_score_gemma":0.001356428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005004635,"about_ca_topic_score_gemma":0.003648439,"domain_scores_codex":[0.9989434,0.0002717259,0.0001269077,0.0002586652,0.0003264285,0.00007291229],"domain_scores_gemma":[0.9983462,0.001048688,0.00006563004,0.000190222,0.0002852851,0.00006402333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001112205,0.000189988,0.001214833,0.001712063,0.0001754105,0.00004481399,0.00006884009,0.02138134,0.0008955809,0.01535821,0.02121508,0.9376326],"study_design_scores_gemma":[0.00008811312,0.0006180462,0.002873169,0.001581694,0.0003397272,0.000650513,0.0002759956,0.6828272,0.005538648,0.09367156,0.2114123,0.0001230089],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01228383,0.4809479,0.4814491,0.004618121,0.0008184144,0.0002183276,0.001000833,0.001895186,0.01676829],"genre_scores_gemma":[0.183354,0.4729781,0.311112,0.003848821,0.002887578,0.0005259345,0.005251622,0.0007273487,0.01931461],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.005509849,"threshold_uncertainty_score":0.01843232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03256208355514538,"score_gpt":0.2880512037855091,"score_spread":0.2554891202303637,"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."}}