Approximating vision transformers for edge: variational inference and mixed-precision for multi-modal data

Katare, DewantDewantKatareLeroux, SamSamLerouxJanssen, MarijnMarijnJanssenDing, Aaron YiAaron YiDing2025-02-202025-02-192025-02-2020250010-485XWOS:001420242600001https://imec-publications.be/handle/20.500.12860/45236Approximating vision transformers for edge: variational inference and mixed-precision for multi-modal dataJournal article10.1007/s00607-025-01427-wWOS:001420242600001