{"id":"W4366984249","doi":"10.1007/s11265-023-01865-9","title":"A Triplet-loss Dilated Residual Network for High-Resolution Representation Learning in Image Retrieval","year":2023,"lang":"en","type":"article","venue":"Journal of Signal Processing Systems","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Artificial intelligence; Computer science; Residual; Image retrieval; Pooling; Pattern recognition (psychology); Convolutional neural network; Robustness (evolution); Precision and recall; Computer vision; Image (mathematics); Algorithm","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":[0.001000004,0.0007748153,0.001130574,0.0005484337,0.0003531964,0.0006539047,0.001982473,0.001638694,0.003681964],"category_scores_gemma":[0.00174082,0.0004097465,0.000616155,0.0008115283,0.0005097769,0.001509432,0.001235827,0.001471035,0.001351246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005443471,"about_ca_system_score_gemma":0.000809113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006155477,"about_ca_topic_score_gemma":0.006494964,"domain_scores_codex":[0.9996654,0.00007483119,0.000020186,0.00009937907,0.0000902251,0.00005001337],"domain_scores_gemma":[0.9995686,0.0001287894,0.00003915165,0.00007495366,0.0001512604,0.00003719613],"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":[0.0004129869,0.00030723,0.0006117939,0.0001670097,0.0001311154,0.0001305043,0.00007213414,0.260932,0.03189974,0.01009785,0.01043086,0.6848067],"study_design_scores_gemma":[0.000007535787,0.00006213362,0.00007933048,0.000004706349,0.00001235831,0.00002707447,0.000004507164,0.9956196,0.002305484,0.001268315,0.0006030257,0.000005889246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01664719,0.0007799113,0.9799658,0.000199611,0.0001066175,0.00005058941,0.0001110942,0.0009577834,0.001181362],"genre_scores_gemma":[0.4634221,0.001125156,0.5190229,0.0005037388,0.0002126615,0.0001931655,0.00117594,0.0002743373,0.01407008],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006155477,"threshold_uncertainty_score":0.01231736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02947200411002551,"score_gpt":0.3159421412791441,"score_spread":0.2864701371691186,"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."}}