Huihong Shi

activity

20212025

most citedShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer

6 citations · 19 across the 18 of their papers we have counts for

collaborators

Showing cs.AIShow all

1 paper · 1 filter

cs.AI2024

P $^{2}$ -ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer

Huihong Shi, Xin Cheng, Wendong Mao +1

Vision Transformers (ViTs) have excelled in computer vision tasks but are memory-consuming and computation-intensive, challenging their deployment on resource-constrained devices.…

P2-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer

P $^{2}$ -ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer