Saved in:
Bibliographic Details
Main Authors: Kim, Minjun, Kim, Jongjin, Kang, U
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.18423
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914408667545600
author Kim, Minjun
Kim, Jongjin
Kang, U
author_facet Kim, Minjun
Kim, Jongjin
Kang, U
contents How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and practical scenario where training data are inaccessible for privacy or security reasons. However, three significant challenges hinder the performance of existing ZSQ methods: 1) noise in the synthetic dataset, 2) predictions based on off-target patterns, and the 3) misguidance by erroneous hard labels. In this paper, we propose SynQ (Synthesis-aware Fine-tuning for Zero-shot Quantization), a carefully designed ZSQ framework to overcome the limitations of existing methods. SynQ minimizes the noise from the generated samples by exploiting a low-pass filter. Then, SynQ trains the quantized model to improve accuracy by aligning its class activation map with the pre-trained model. Furthermore, SynQ mitigates misguidance from the pre-trained model's error by leveraging only soft labels for difficult samples. Extensive experiments show that SynQ provides the state-of-the-art accuracy, over existing ZSQ methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18423
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
Kim, Minjun
Kim, Jongjin
Kang, U
Computer Vision and Pattern Recognition
How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and practical scenario where training data are inaccessible for privacy or security reasons. However, three significant challenges hinder the performance of existing ZSQ methods: 1) noise in the synthetic dataset, 2) predictions based on off-target patterns, and the 3) misguidance by erroneous hard labels. In this paper, we propose SynQ (Synthesis-aware Fine-tuning for Zero-shot Quantization), a carefully designed ZSQ framework to overcome the limitations of existing methods. SynQ minimizes the noise from the generated samples by exploiting a low-pass filter. Then, SynQ trains the quantized model to improve accuracy by aligning its class activation map with the pre-trained model. Furthermore, SynQ mitigates misguidance from the pre-trained model's error by leveraging only soft labels for difficult samples. Extensive experiments show that SynQ provides the state-of-the-art accuracy, over existing ZSQ methods.
title SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.18423