{"id":"W4210768747","doi":"10.1145/3472393","title":"RD-IOD: Two-Level Residual-Distillation-Based Triple-Network for Incremental Object Detection","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Beijing Municipal Science and Technology Commission; National Natural Science Foundation of China","keywords":"Computer science; Residual; Artificial intelligence; Object (grammar); Convolutional neural network; Forgetting; Distillation; Machine learning; Feature (linguistics); Learning object; Object detection; Pattern recognition (psychology); 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":[0.0008802371,0.001421276,0.001317176,0.000658484,0.0004701107,0.0008834663,0.004313123,0.001335566,0.002678954],"category_scores_gemma":[0.001991296,0.0006631153,0.0009889991,0.0005666753,0.0009389489,0.002559096,0.0026164,0.002320812,0.0009743106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094295,"about_ca_system_score_gemma":0.001335755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006160768,"about_ca_topic_score_gemma":0.007980619,"domain_scores_codex":[0.9994456,0.00005286816,0.00002410189,0.0002233967,0.0001466471,0.0001073474],"domain_scores_gemma":[0.9994581,0.0001428589,0.00005486175,0.0001294806,0.0001468434,0.00006795701],"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":[0.0004971407,0.0003215408,0.002716881,0.0002426969,0.0001748982,0.0004266021,0.0002593706,0.2116568,0.0426517,0.02402691,0.01043318,0.7065923],"study_design_scores_gemma":[0.000009480235,0.00006680687,0.0001521796,0.000008038945,0.00002167003,0.0000724268,0.00000817472,0.9867958,0.007213701,0.004080012,0.001555433,0.00001634243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01941669,0.0005352671,0.9735931,0.0001743208,0.0001051819,0.00008568418,0.0001434279,0.003862984,0.002083357],"genre_scores_gemma":[0.4947597,0.0004881744,0.4915817,0.0006708703,0.0000951246,0.0002601486,0.001474139,0.0004689772,0.01020118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006160768,"threshold_uncertainty_score":0.01224983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04402762313761858,"score_gpt":0.3098828924033286,"score_spread":0.26585526926571,"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."}}