research
∙
05/24/2023
BinaryViT: Towards Efficient and Accurate Binary Vision Transformers
Vision Transformers (ViTs) have emerged as the fundamental architecture ...
share
research
∙
05/11/2023
Patch-wise Mixed-Precision Quantization of Vision Transformer
As emerging hardware begins to support mixed bit-width arithmetic comput...
research
∙
12/16/2022
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
Post-training quantization (PTQ), which only requires a tiny dataset for...
research
∙
09/13/2022
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers
Data-free quantization can potentially address data privacy and security...
research
∙
07/04/2022
I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
Vision Transformers (ViTs) have achieved state-of-the-art performance on...
research
∙
03/04/2022