{"id":"W3172122468","doi":"","title":"Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection","year":2021,"lang":"en","type":"article","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Nvidia","keywords":"Resampling; Computer science; Artificial intelligence; Object (grammar); Feature (linguistics); Object detection; Image segmentation; Image (mathematics); Pattern recognition (psychology); Segmentation; Computation; Computer vision; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005719731,0.000288427,0.0005476142,0.0007241915,0.0002751179,0.0001060342,0.0009402164,0.0003650862,0.00002644983],"category_scores_gemma":[0.001227304,0.0002704728,0.0002011509,0.001994288,0.0004782199,0.000637156,0.0004002177,0.000437203,0.00002280191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008878178,"about_ca_system_score_gemma":0.0007016487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002606293,"about_ca_topic_score_gemma":0.0002585303,"domain_scores_codex":[0.9976684,0.00004468665,0.0008026102,0.0006693947,0.0003323824,0.0004825322],"domain_scores_gemma":[0.9977084,0.0001039797,0.000501346,0.0008596477,0.0007241796,0.0001024664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002576184,0.0003716811,0.0005175318,0.0007791743,0.0002220702,0.0001764526,0.0005320603,0.003291637,0.4294124,0.2506101,0.0001801288,0.3136492],"study_design_scores_gemma":[0.00405432,0.0006949819,0.0005236221,0.0005522335,0.0001068683,0.0003265751,0.001825531,0.1078771,0.7739273,0.07712376,0.03198701,0.00100069],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06537613,0.0001630628,0.9318185,0.0006803374,0.000597737,0.0004319981,0.0001050544,0.0004896973,0.0003374183],"genre_scores_gemma":[0.5399094,0.00002347267,0.4597042,0.00004392613,0.00003262843,0.00008378047,0.00001811259,0.0000207958,0.0001637348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4745332,"threshold_uncertainty_score":0.9999747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05821363653058965,"score_gpt":0.3115166592768869,"score_spread":0.2533030227462973,"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."}}