SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning


METADATA ONLY
Loading...

Date

2022

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult. Considering the computation complexity, the internal data pattern of ViTs, and the edge device deployment, we propose a latency-aware soft token pruning framework, SPViT, which can be set up on vanilla Transformers of both flatten and hierarchical structures, such as DeiTs and Swin-Transformers (Swin). More concretely, we design a dynamic attention-based multi-head token selector, which is a lightweight module for adaptive instance-wise token selection. We further introduce a soft pruning technique, which integrates the less informative tokens chosen by the selector module into a package token rather than discarding them completely. SPViT is bound to the trade-off between accuracy and latency requirements of specific edge devices through our proposed latency-aware training strategy. Experiment results show that SPViT significantly reduces the computation cost of ViTs with comparable performance on image classification. Moreover, SPViT can guarantee the identified model meets the latency specifications of mobile devices and FPGA, and even achieve the real-time execution of DeiT-T on mobile devices. For example, SPViT reduces the latency of DeiT-T to 26 ms (26%-41% superior to existing works) on the mobile device with 0.25%-4% higher top-1 accuracy on ImageNet. Our code is released at https://github.com/PeiyanFlying/SPViT.

Publication status

published

Book title

Computer Vision – ECCV 2022

Volume

13671

Pages / Article No.

620 - 640

Publisher

Springer

Event

17th European Conference on Computer Vision (ECCV 2022)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Vision transformer; Model compression; Hardware acceleration; Mobile devices; FPGA

Organisational unit

Notes

Funding

Related publications and datasets