{"id":"W3208470653","doi":"10.1109/iccvw54120.2021.00091","title":"Knowledge Distillation for Low-Power Object Detection: A Simple Technique and Its Extensions for Training Compact Models Using Unlabeled Data","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Distillation; Computer science; Simple (philosophy); Artificial intelligence; Object (grammar); Training set; Training (meteorology); Machine learning; Object detection; Power (physics); Pattern recognition (psychology); Chromatography; Chemistry","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":[0.002423584,0.00209995,0.001693151,0.001061615,0.0007361156,0.00156899,0.003555519,0.002320943,0.004243269],"category_scores_gemma":[0.006525284,0.001023853,0.001202779,0.001170228,0.001976273,0.004823647,0.004448774,0.005086225,0.001925452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008299435,"about_ca_system_score_gemma":0.001712087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003782283,"about_ca_topic_score_gemma":0.007980317,"domain_scores_codex":[0.9988667,0.0002832539,0.00004463187,0.000467136,0.0002272407,0.0001111234],"domain_scores_gemma":[0.9975898,0.001143778,0.0001532984,0.0007765195,0.0002149818,0.0001215419],"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":[0.0004405073,0.0003554806,0.001471449,0.0003476581,0.0001973986,0.0002120161,0.00036068,0.2209952,0.02746568,0.03403594,0.007236863,0.7068811],"study_design_scores_gemma":[0.00003298831,0.0000871609,0.0002149009,0.00002490538,0.00002211982,0.00007916912,0.00002586898,0.9572362,0.01046791,0.02875216,0.003027135,0.00002946958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00883068,0.0002810549,0.9871904,0.0002235523,0.00005142363,0.0000537108,0.0001119931,0.002475618,0.0007815017],"genre_scores_gemma":[0.3008945,0.0004054423,0.6887273,0.0006381721,0.0001711422,0.0003450605,0.001022153,0.0005692886,0.007226819],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004243269,"threshold_uncertainty_score":0.01419508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.190347442643677,"score_gpt":0.377449432259311,"score_spread":0.187101989615634,"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."}}