{"id":"W3205652345","doi":"10.1109/cvpr52688.2022.01213","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"FLOPS; Computer science; Regularization (linguistics); Hyperparameter; Artificial intelligence; Reduction (mathematics); Artificial neural network; Machine learning; Pruning; Computational complexity theory; Pattern recognition (psychology); Algorithm; Mathematics","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":[0.000821267,0.00139897,0.001475485,0.0007002201,0.0007412774,0.001019671,0.003615393,0.001774803,0.002158693],"category_scores_gemma":[0.002478695,0.0008595798,0.000819084,0.0006039796,0.0008722579,0.002447059,0.001733691,0.001683838,0.0009332969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008543248,"about_ca_system_score_gemma":0.001288836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004340407,"about_ca_topic_score_gemma":0.008142913,"domain_scores_codex":[0.9994318,0.0000834102,0.00002391733,0.0001734796,0.0001885565,0.00009876239],"domain_scores_gemma":[0.9988468,0.0003576315,0.0001394155,0.000333047,0.0002353325,0.00008781748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000421969,0.0003225558,0.002643119,0.0001000065,0.0002150277,0.0003568378,0.0002989632,0.4787534,0.02405054,0.01058948,0.01095461,0.4712936],"study_design_scores_gemma":[0.000009035639,0.00003305975,0.0001445661,0.000004995343,0.00001423417,0.00003773994,0.000009557143,0.9925816,0.002697613,0.003881426,0.0005809374,0.000005355543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05230701,0.0004814778,0.9399123,0.0004501976,0.00008493067,0.00008012551,0.0001154528,0.003876017,0.002692536],"genre_scores_gemma":[0.7041215,0.0002226226,0.2855793,0.0005862574,0.0001571444,0.0001953402,0.0005403994,0.0006618808,0.007935581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004340407,"threshold_uncertainty_score":0.008630276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02583837965759348,"score_gpt":0.2467557511212553,"score_spread":0.2209173714636618,"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."}}