Patch Similarity Aware Data-Free Quantization for Vision Transformers
Open accessIntegrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
PSAQ-ViT introduced a Data-Free Quantization approach for ViTs, which eschews the need for real images during calibration.
“PSAQ-ViT [56] introduced an innovative Data-Free Quantization approach for ViTs, which eschews the need for real images during calibration.”
From Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey (2024) · cites this paper as [56]
Vision Transformers suffer from higher memory footprints, computational overheads, and power consumption than convolutional neural networks, hindering their deployment and real-time inference on resource-constrained edge devices.
“Nevertheless, as compared to convolutional neural networks (CNNs), ViTs suffer from higher memory footprints, computational overheads, and power consumption, hindering their deployment and real-time inference on resourceconstrained edge devices [25, 17, 15, 37].”
From I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference (2023) · cites this paper as [25]
Cites
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534 · see citing works
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285 · see citing works
Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., & Lu, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00803 · Cited by 1,588 · cited 1× · see citing works
“great success on various computer vision tasks [1, 6, 15, 33, 40].”
BackgroundHan, K., Xiao, A., Wu, E., Guo, J., Xu, C., & Wang, Y. (2021) · arXiv · doi:10.48550/arxiv.2103.00112 · Cited by 1,394 · cited 1× · see citing works
“great success on various computer vision tasks [1, 6, 15, 33, 40].”
BackgroundA Survey of Quantization Methods for Efficient Neural Network Inference
Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M. W., & Keutzer, K. (2022) · Low-Power Computer Vision · doi:10.1201/9781003162810-13 · Cited by 1,219 · cited 2× · see citing works
“Model quantization, which reduces the memory footprint and computational overhead of the models by decreasing the representation precision of the weights and activations, is an effective approach to compressing models in a hardware-friendly manner [13, 20].”
BackgroundLow-bit Quantization of Neural Networks for Efficient Inference
Choukroun, Y., Kravchik, E., Yang, F., & Kisilev, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00363 · Cited by 404 · see citing works
Patch Slimming for Efficient Vision Transformers
Tang, Y., Han, K., Wang, Y., Xu, C., Guo, J., Xu, C., & Tao, D. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01185 · Cited by 201 · see citing works
PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization
Yuan, Z., Xue, C., Chen, Y., Wu, Q., & Sun, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19775-8_12 · Cited by 163 · cited 1× · see citing works
“In addition, several post-training quantization methods have been proposed to reduce the fine-tuning cost [9,17,22,24,27,32], including schemes for vision transformers [26,36], but they still require a small amount of real data for calibration and cannot achieve complete data-free.”
BackgroundI-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
Li, Z., & Gu, Q. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01565 · Cited by 141 · cited 1× · see citing works
“The mainstream methods exploit quantization-aware training to compensate the accuracy degradation caused by discretization [39, 23, 25, 8, 12], and they use the straight-through estimator [2] to approximate the gradient back-propagation of the quantized model.”
MethodSelf-citation
Flagged first, then by citations
Cited by
Sorted by citations
A Survey of Techniques for Optimizing Transformer Inference
Chitty-Venkata, K. T., Mittal, S., Emani, M., Vishwanath, V., & Somani, A. K. (2023) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2023.102990 · Cited by 154 · see citing works
I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
Li, Z., & Gu, Q. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01565 · Cited by 141 · see citing works
“PSAQ-ViT [15] pushes the quantization of ViTs to data-free scenarios based on patch similarity.”
BackgroundMethodSelf-citationRepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
Li, Z., Xiao, J., Yang, L., & Gu, Q. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01580 · Cited by 127 · see citing works
Self-citationPSAQ-ViT V2: Toward Accurate and General Data-Free Quantization for Vision Transformers
Li, Z., Chen, M., Xiao, J., & Gu, Q. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3301007 · Cited by 41 · see citing works
Self-citationJumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
Frumkin, N., Gope, D., & Marculescu, D. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01557 · Cited by 14 · see citing works
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-training Quantization of ViTs
Ramachandran, A., Kundu, S., & Krishna, T. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72855-6_18 · Cited by 14 · see citing works
Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey
Du, D., Gong, G., & Chu, X. (2024) · arXiv · doi:10.48550/arxiv.2405.00314 · Cited by 4 · see citing works
“5) Data-Free Calibration : PSAQ-ViT [56] introduced an innovative Data-Free Quantization approach for ViTs, which eschews the need for real images during calibration.”
BackgroundMethodTask-Specific Zero-Shot Quantization-Aware Training for Object Detection
Li, C., Chen, X., Wang, J., Zhao, K., & Chen, J. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02123 · Cited by 2 · see citing works
Zero-shot quantization for object detection via scene-aware synthesis and instance-guided alignment
Li, X., Di, X., Liu, M., & Ye, S. (2026) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-026-00412-z · Cited by 1 · see citing works
- Authors
- Li, Z., Ma, L., Chen, M., Xiao, J., & Gu, Q.
- Affiliations
- Chinese Academy of Sciences (CN)
- Corresponding author
- Gu, Qingyi
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Nature Switzerland
- Published
- 2022
- Pages
- 154-170
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W4309125142
- Cited by
- 61
- References
- 9
- Citations by year
- 2026: 10 · 2025: 27 · 2024: 12 · 2023: 12
- FWCI
- 4.62
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Lecture notes in computer science (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62276255)
- Chinese Academy of Sciences (YJKYYQ20200045)
- 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 › Adversarial Robustness in Machine Learning
- Keywords
- data-free quantization, vision transformer, patch similarity, self-attention, Gaussian noise, model compression, resource-constrained deployment
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
