{"id":"W7131074035","doi":"10.1109/iccvw69036.2025.00422","title":"Enhancing Generalization in Data-Free Quantization via Mixup-Class Prompting","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hyperion Technologies (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Quantization (signal processing); Generalizability theory; Generative grammar; Synthetic data; Convolutional neural network; Vector quantization; Adversarial system; Generalization; Source code","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":[0.001467013,0.0009560051,0.0007134043,0.0004396689,0.0004030149,0.0009769319,0.001256017,0.0009419839,0.004439749],"category_scores_gemma":[0.009725652,0.0002997321,0.0004749305,0.0005656804,0.001066727,0.002672973,0.002392889,0.002398246,0.001378463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006532263,"about_ca_system_score_gemma":0.0007996815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00130512,"about_ca_topic_score_gemma":0.001892337,"domain_scores_codex":[0.9991034,0.0002149125,0.00004966347,0.0002696612,0.0002810688,0.00008129424],"domain_scores_gemma":[0.9973781,0.001199429,0.0001568605,0.0007840452,0.0003847778,0.00009687277],"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":[0.0006639754,0.0002777131,0.002060618,0.0002165589,0.00004269767,0.0002227158,0.0004066009,0.2671154,0.05070594,0.02281405,0.01223703,0.6432368],"study_design_scores_gemma":[0.00004693085,0.000124328,0.000428685,0.00002273095,0.00001042333,0.0001066905,0.00007316922,0.9452436,0.02808458,0.02210557,0.003726805,0.00002654184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04268968,0.000351416,0.9487787,0.0004624026,0.0001284853,0.00008933202,0.0002977203,0.005022904,0.002179335],"genre_scores_gemma":[0.6792992,0.0002994337,0.3121045,0.0007119302,0.00009517893,0.0002483884,0.001074946,0.0008995737,0.005266883],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004439749,"threshold_uncertainty_score":0.0148524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03167382510845623,"score_gpt":0.3309409491838378,"score_spread":0.2992671240753815,"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."}}