{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007941016,0.0001560089,0.0002435984,0.0004120828,0.0006419688,0.0001210439,0.000525514,0.00003326576,0.0001247911],"category_scores_gemma":[0.00001834698,0.0001509104,0.0002078723,0.001876332,0.00004248813,0.000167088,0.00001113242,0.0003474732,0.000004820899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006226169,"about_ca_system_score_gemma":0.00002176799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003816769,"about_ca_topic_score_gemma":0.0003372938,"domain_scores_codex":[0.9984277,0.0002343387,0.0003210927,0.0005020788,0.0003084117,0.0002063054],"domain_scores_gemma":[0.9989915,0.0003009783,0.0001357659,0.0003738796,0.0001207282,0.00007709216],"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":[0.00005656797,0.0001611817,0.0009261215,0.00001293629,0.0002294752,0.000002663009,0.0003203997,0.01739382,0.0004927793,0.0002112837,0.000006412155,0.9801863],"study_design_scores_gemma":[0.0001008431,0.000350669,0.002439033,0.000004424367,0.0001404961,0.000007582626,0.00006918141,0.8713887,0.1240048,0.0004002954,0.0008018982,0.0002921388],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005984312,0.0001546865,0.9984405,0.0002695842,0.0001211871,0.0001841862,0.00003790628,0.0001652871,0.00002820405],"genre_scores_gemma":[0.9964282,0.0002767898,0.002334432,0.0003105424,0.000006837933,0.00007494978,0.00001558353,0.00001091498,0.0005417755],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9961061,"threshold_uncertainty_score":0.6153948,"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."}}