{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002582578,0.001005804,0.001124381,0.0006416093,0.0003511301,0.001475104,0.001702395,0.0014796,0.001825128],"category_scores_gemma":[0.007021716,0.0004859762,0.0006278899,0.0006190632,0.00142202,0.003976687,0.001593891,0.00272759,0.001379342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007078922,"about_ca_system_score_gemma":0.0006606552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002083815,"about_ca_topic_score_gemma":0.003783744,"domain_scores_codex":[0.9991577,0.0001884018,0.00004227097,0.000341495,0.0001746889,0.00009544088],"domain_scores_gemma":[0.9979982,0.0005654237,0.0001324055,0.0009757319,0.000213785,0.0001143835],"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":[0.0005099328,0.0002287876,0.004872214,0.0001834857,0.0001807739,0.0001425845,0.0003069239,0.04511862,0.04665644,0.02980021,0.01127739,0.8607227],"study_design_scores_gemma":[0.00005956364,0.0003873669,0.00519503,0.00009412305,0.0001061449,0.0007189394,0.0002056199,0.8149473,0.07810618,0.08094551,0.01911,0.0001241544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02876767,0.001817188,0.9620327,0.002335256,0.000257344,0.00007460282,0.0001461621,0.002660185,0.001908946],"genre_scores_gemma":[0.4987543,0.001220088,0.4903098,0.001867797,0.0004920649,0.0001458963,0.0007166067,0.000666366,0.005827147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002582578,"threshold_uncertainty_score":0.01365817,"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."}}