Towards efficient vision transformer inference
Xudong Wang, Li Lyna Zhang, Yang Wang, Mao Yang
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