Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.

PSAQ-ViT V2: Toward Accurate and General Data-Free Quantization for Vision Transformers

Li, Zhikai, Chen, Mengjuan, Xiao, Junrui, Gu, Qingyi · 2024 · IEEE Transactions on Neural Networks and Learning Systems

Abstract

Data-free quantization can potentially address data privacy and security concerns in model compression and thus has been widely investigated. Recently, patch similarity aware data-free quantization for vision transformers (PSAQ-ViT) designs a relative value metric, patch similarity, to generate data from pretrained vision transformers (ViTs), achieving the first attempt at data-free quantization for ViTs. In this article, we propose PSAQ-ViT V2, a more accurate and general data-free quantization framework for ViTs, built on top of PSAQ-ViT. More specifically, following the patch similarity metric in PSAQ-ViT, we introduce an adaptive teacher-student strategy, which facilitates the constant cyclic evolution of the generated samples and the quantized model (student) in a competitive and interactive fashion under the supervision of the full-precision (FP) model (teacher), thus significantly improving the accuracy of the quantized model. Moreover, without the auxiliary category guidance, we employ the task- and model-independent prior information, making the general-purpose scheme compatible with a broad range of vision tasks and models. Extensive experiments are conducted on various models on image classification, object detection, and semantic segmentation tasks, and PSAQ-ViT V2, with the naive quantization strategy and without access to real-world data, consistently achieves competitive results, showing potential as a powerful baseline on data-free quantization for ViTs. For instance, with Swin-S as the (backbone) model, 8-bit quantization reaches 82.13 top-1 accuracy on ImageNet, 50.9 box AP and 44.1 mask AP on COCO, and 47.2 mean Intersection over Union (mIoU) on ADE20K. We hope that accurate and general PSAQ-ViT V2 can serve as a potential and practice solution in real-world applications involving sensitive data. Code is released and merged at: https://github.com/zkkli/PSAQ-ViT.

Overview

Integrity signals

Registry

Crossref · 10.1109/tnnls.2023.3301007

Cites

61 of 61 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 60 references

Research works printed but not linked: 4

  1. Dosovitskiy, An image is worth 16×16 words: Transformers for image recognition at scale, 1
  2. 10.5555/3524938.3525087 · doi:10.5555/3524938.3525087
  3. Wightman, 2019, PyTorch Image Models
  4. 2020, MMSegmentation: Openmmlab Semantic Segmentation Toolbox and Benchmark

Cited by

See all 58

Metadata

Authors
Li, Z., Chen, M., Xiao, J., & Gu, Q.
Affiliations
Chinese Academy of Sciences (CN)
Venue
IEEE Transactions on Neural Networks and Learning Systems
Published
2024-12
Volume
35
Issue
12
Pages
17227-17238
ISSN
  • 2162-237X (ISSN-L)
  • 2162-2388
OpenAlex
W4385819842
Cited by
41
References
60
Citations by year
2026: 8 · 2025: 23 · 2024: 7
FWCI
3.73
Type
journal article
Language
en
Open access
closed
Locations
  • IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
  • PubMed (publishedVersion)
Funders
  • National Key Research and Development Program of China (2022ZD0119402)
  • National Natural Science Foundation of China (62276255)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
Keywords
data-free quantization, vision transformer, patch similarity, model compression, data privacy, 8-bit quantization, Swin Transformer, image classification, object detection, semantic segmentation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: PSAQ-ViT V2: Toward Accurate and General Data-Free Quantization for Vision Transformers. https://app.cochat.ai/papers/10.1109/tnnls.2023.3301007
The paper
Li, Z., Chen, M., Xiao, J., & Gu, Q. (2024). PSAQ-ViT V2: Toward Accurate and General Data-Free Quantization for Vision Transformers. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1109/tnnls.2023.3301007

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.