{"id":"W4385801596","doi":"10.1109/cvprw59228.2023.00499","title":"CFDP: Common Frequency Domain Pruning","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Robustness (evolution); Pruning; Artificial neural network; Trimming; FLOPS; Feature (linguistics); Pipeline (software); Artificial intelligence; Machine learning; Deep neural networks; Frequency domain; Domain (mathematical analysis); Interoperability; Parallel computing; 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":[0.0008937901,0.001759979,0.001061819,0.001110911,0.0007706114,0.001288945,0.002721816,0.001835318,0.00535326],"category_scores_gemma":[0.003475622,0.000605421,0.001129041,0.0007694073,0.0008568835,0.002041752,0.002470099,0.002802918,0.002308708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008381851,"about_ca_system_score_gemma":0.001629118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009381403,"about_ca_topic_score_gemma":0.01476156,"domain_scores_codex":[0.9994891,0.00008216954,0.00002701315,0.0001510478,0.0001769597,0.00007369543],"domain_scores_gemma":[0.999181,0.0002565256,0.00005317045,0.0003170016,0.0001513254,0.00004111076],"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":[0.0002460542,0.0001977605,0.002235424,0.00023445,0.0002110182,0.0005288416,0.000181389,0.4089797,0.01735187,0.02712072,0.04651703,0.4961957],"study_design_scores_gemma":[0.00002371998,0.00004076887,0.0002136091,0.00001998038,0.0000197083,0.0001615212,0.00002099082,0.9670405,0.007566428,0.01892263,0.00595684,0.00001336616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01396034,0.0005024052,0.9711421,0.0003285509,0.0001345895,0.0001105858,0.0005435664,0.00993752,0.00334038],"genre_scores_gemma":[0.3385358,0.0004800819,0.6460158,0.0008555445,0.0001164935,0.000356319,0.00354696,0.001602514,0.008490506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009381403,"threshold_uncertainty_score":0.01865363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02510502534555889,"score_gpt":0.2701033692254175,"score_spread":0.2449983438798586,"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."}}