{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002795065,0.000157533,0.000409844,0.0004303659,0.0002356926,0.0003925755,0.0004670706,0.0001171938,9.613935e-7],"category_scores_gemma":[0.0004962127,0.0001388344,0.0000897335,0.002083976,0.0000448738,0.001901799,0.00007919877,0.0004267491,0.000003530901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000151793,"about_ca_system_score_gemma":0.0002097679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000176938,"about_ca_topic_score_gemma":7.799992e-7,"domain_scores_codex":[0.9975028,0.0002401168,0.000986055,0.0002808685,0.0005815891,0.0004085594],"domain_scores_gemma":[0.9977028,0.0003457807,0.001070767,0.000138804,0.0006622716,0.00007952659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005663888,0.0004202953,0.009912118,0.002669063,0.0002635235,0.002429542,0.005938439,0.3262768,0.3767667,0.006403227,0.02747504,0.2357814],"study_design_scores_gemma":[0.005913311,0.002957083,0.008486681,0.005373655,0.00008453897,0.0007844255,0.000914274,0.8590748,0.07869063,0.03233014,0.004331141,0.001059335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03071904,0.001061577,0.9668933,0.0003940309,0.000327172,0.0003308153,0.000001552633,0.0002426287,0.00002994302],"genre_scores_gemma":[0.9629496,0.00008996948,0.03577704,0.00002372212,0.0008255145,0.0000106371,0.000007395814,0.0000247459,0.0002913453],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9322306,"threshold_uncertainty_score":0.5661501,"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."}}