Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhong, Yunshan, Zhou, Yuyao, Zhang, Yuxin, Sui, Wanchen, Li, Shen, Li, Yong, Chao, Fei, Ji, Rongrong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908621610156032
author Zhong, Yunshan
Zhou, Yuyao
Zhang, Yuxin
Sui, Wanchen
Li, Shen
Li, Yong
Chao, Fei
Ji, Rongrong
author_facet Zhong, Yunshan
Zhou, Yuyao
Zhang, Yuxin
Sui, Wanchen
Li, Shen
Li, Yong
Chao, Fei
Ji, Rongrong
contents Data-free quantization (DFQ) enables model quantization without accessing real data, addressing concerns regarding data security and privacy. With the growing adoption of Vision Transformers (ViTs), DFQ for ViTs has garnered significant attention. However, existing DFQ methods exhibit two limitations: (1) semantic distortion, where the semantics of synthetic images deviate substantially from those of real images, and (2) semantic inadequacy, where synthetic images contain extensive regions with limited content and oversimplified textures, leading to suboptimal quantization performance. To address these limitations, we propose SARDFQ, a novel Semantics Alignment and Reinforcement Data-Free Quantization method for ViTs. To address semantic distortion, SARDFQ incorporates Attention Priors Alignment (APA), which optimizes synthetic images to follow randomly generated structure attention priors. To mitigate semantic inadequacy, SARDFQ introduces Multi-Semantic Reinforcement (MSR), leveraging localized patch optimization to enhance semantic richness across synthetic images. Furthermore, SARDFQ employs Soft-Label Learning (SL), wherein multiple semantic targets are adapted to facilitate the learning of multi-semantic images augmented by MSR. Extensive experiments demonstrate the effectiveness of SARDFQ, significantly surpassing existing methods. For example, SARDFQ improves top-1 accuracy on ImageNet by 15.52% for W4A4 ViT-B. The code is at https://github.com/zysxmu/SARDFQ.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16553
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
Zhong, Yunshan
Zhou, Yuyao
Zhang, Yuxin
Sui, Wanchen
Li, Shen
Li, Yong
Chao, Fei
Ji, Rongrong
Computer Vision and Pattern Recognition
Data-free quantization (DFQ) enables model quantization without accessing real data, addressing concerns regarding data security and privacy. With the growing adoption of Vision Transformers (ViTs), DFQ for ViTs has garnered significant attention. However, existing DFQ methods exhibit two limitations: (1) semantic distortion, where the semantics of synthetic images deviate substantially from those of real images, and (2) semantic inadequacy, where synthetic images contain extensive regions with limited content and oversimplified textures, leading to suboptimal quantization performance. To address these limitations, we propose SARDFQ, a novel Semantics Alignment and Reinforcement Data-Free Quantization method for ViTs. To address semantic distortion, SARDFQ incorporates Attention Priors Alignment (APA), which optimizes synthetic images to follow randomly generated structure attention priors. To mitigate semantic inadequacy, SARDFQ introduces Multi-Semantic Reinforcement (MSR), leveraging localized patch optimization to enhance semantic richness across synthetic images. Furthermore, SARDFQ employs Soft-Label Learning (SL), wherein multiple semantic targets are adapted to facilitate the learning of multi-semantic images augmented by MSR. Extensive experiments demonstrate the effectiveness of SARDFQ, significantly surpassing existing methods. For example, SARDFQ improves top-1 accuracy on ImageNet by 15.52% for W4A4 ViT-B. The code is at https://github.com/zysxmu/SARDFQ.
title Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.16553