Litcius/Paper detail

Towards efficient vision transformer inference

Xudong Wang, Li Lyna Zhang, Yang Wang, Mao Yang

202247 citationsDOI

Abstract

Convolution neural networks (CNNs) have long been dominating the model choice in on-device intelligent mobile applications. Recently, we are witnessing the fast development of vision transformers, which are notable for the use of the self-attention mechanism, have demonstrated the superiority in accuracy over CNNs. However, vision transformers are with expensive computation costs, and their inference efficiency on resource-constrained mobile devices are still unclear by now. This brings a lot of uncertainty for on-device intelligence to benefit from the vision transformers.

Topics & Concepts

InferenceTransformerComputer scienceComputationConvolutional neural networkArtificial intelligenceMobile deviceArtificial neural networkMachine learningEngineeringElectrical engineeringVoltageAlgorithmOperating systemCCD and CMOS Imaging SensorsAdvanced Memory and Neural ComputingAdvanced Neural Network Applications
Towards efficient vision transformer inference | Litcius