{"id":"W4309208755","doi":"10.48550/arxiv.2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"CCD and CMOS Imaging Sensors","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Security token; Computation; Quantization (signal processing); Computer hardware; Hardware acceleration; Edge device; Field-programmable gate array; Computer engineering; Latency (audio); Algorithm; Computer network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003308585,0.0006982813,0.0005387022,0.0005352854,0.0003816045,0.0007990741,0.002049791,0.0004077937,0.004374442],"category_scores_gemma":[0.001373808,0.0003042975,0.0004034008,0.0004732323,0.0004531533,0.001717389,0.0009841907,0.0009222364,0.0009985893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000891365,"about_ca_system_score_gemma":0.001448702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006010141,"about_ca_topic_score_gemma":0.01152121,"domain_scores_codex":[0.9997219,0.00002200139,0.00001759005,0.00006573395,0.0001175695,0.00005508266],"domain_scores_gemma":[0.9996985,0.00007251662,0.00003506307,0.00007631518,0.00008432976,0.00003321494],"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":[0.0008834506,0.0001522266,0.003266743,0.0003207181,0.00009984753,0.0003044655,0.0001777922,0.1119679,0.09952421,0.02154638,0.01892101,0.7428352],"study_design_scores_gemma":[0.00005437574,0.0002182631,0.0006808236,0.00002161342,0.00004240736,0.0002134851,0.00004179451,0.9259388,0.05814423,0.005375214,0.009240466,0.00002837759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03953989,0.0007558336,0.9465279,0.0001429799,0.0001503125,0.0001044954,0.0002324725,0.009548672,0.002997559],"genre_scores_gemma":[0.5928214,0.000391209,0.3982996,0.000280522,0.00005300001,0.0001193043,0.0008951834,0.0004271554,0.006712678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006010141,"threshold_uncertainty_score":0.01463395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04724298686371685,"score_gpt":0.1854540897693705,"score_spread":0.1382111029056537,"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."}}