SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection

27 January 2024

Yang Liu

Papers citing "SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection"

3 / 3 papers shown

Title
Accelerating the Low-Rank Decomposed Models Habib Hajimolahoseini Walid Ahmed Austin Wen Yang Liu 64 0 0 24 Jul 2024
GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values Farnoosh Javadi Walid Ahmed Habib Hajimolahoseini Foozhan Ataiefard Mohammad Hassanpour Saina Asani Austin Wen Omar Mohamed Awad Kangling Liu Yang Liu VLM 67 8 0 06 Nov 2023
Training data-efficient image transformers & distillation through attention Hugo Touvron Matthieu Cord Matthijs Douze Francisco Massa Alexandre Sablayrolles Hervé Jégou ViT 273 6,657 0 23 Dec 2020