I-ViT: Integer-only Quantization for Efficient Vision Transformer
Inference

I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference

4 July 2022

Qingyi Gu

Papers citing "I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference"

9 / 59 papers shown

Title
Oscillation-free Quantization for Low-bit Vision Transformers Shi Liu Zechun Liu Kwang-Ting Cheng MQ 23 34 0 04 Feb 2023
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers Zhikai Li Junrui Xiao Lianwei Yang Qingyi Gu MQ 26 81 0 16 Dec 2022
CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers N. Frumkin Dibakar Gope Diana Marculescu ViT MQ 26 1 0 17 Nov 2022
BiViT: Extremely Compressed Binary Vision Transformer Yefei He Zhenyu Lou Luoming Zhang Jing Liu Weijia Wu Hong Zhou Bohan Zhuang ViT MQ 20 28 0 14 Nov 2022
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers Zhikai Li Mengjuan Chen Junrui Xiao Qingyi Gu ViT MQ 43 33 0 13 Sep 2022
Patch Similarity Aware Data-Free Quantization for Vision Transformers Zhikai Li Liping Ma Mengjuan Chen Junrui Xiao Qingyi Gu MQ ViT 17 44 0 04 Mar 2022
Transformer in Transformer Kai Han An Xiao Enhua Wu Jianyuan Guo Chunjing Xu Yunhe Wang ViT 287 1,524 0 27 Feb 2021
I-BERT: Integer-only BERT Quantization Sehoon Kim A. Gholami Z. Yao Michael W. Mahoney Kurt Keutzer MQ 99 341 0 05 Jan 2021
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights Aojun Zhou Anbang Yao Yiwen Guo Lin Xu Yurong Chen MQ 325 1,049 0 10 Feb 2017