Vit Quantization: CPU-Centric Analysis of the Trade-Off between Size and Speed
Main Article Content
Abstract
Using Vision Transformer (ViT) models in real medical practice – for example, in hospitals or diagnostic centers – is often difficult because doctors' work computers usually do not have powerful graphics processors (GPUs), and computing resources are limited. This work investigates a complete practical pipeline for model inference, aimed at reducing computational costs without significant loss of predictive performance.
The proposed approach combines several optimization techniques. First, knowledge distillation (KD) is used, where a compact student model learns to mimic the behavior of a larger, more accurate teacher model. Second, Exponential Moving Average (EMA) of the model weights is applied to stabilize training and improve generalization. Third, post-training INT8 quantization (PTQ) is explored to reduce model size and accelerate inference. Additionally, a simplified quantization-aware training variant (QAT-lite) is considered, where the effects of quantization are partially incorporated during fine-tuning.
Experiments are conducted on the ISIC dataset, which contains dermoscopic images of skin lesions. Model performance is evaluated using standard classification metrics, including accuracy, macro-averaged F1 score, and area under the ROC curve (ROC-AUC). CPU performance is also analyzed, including inference latency, throughput, memory consumption, and the final model size.
The results show that post-training INT8 quantization preserves performance close to the FP32 baseline while substantially reducing memory and computational requirements. In contrast, QAT-lite does not consistently provide reproducible improvements over PTQ.
Article Details
References
2. He K., Gan C., et al. Transformers in Medical Image Analysis: A Review // arXiv. 2022.
3. Atabansi C.C., Nie J., et al. A Survey of Transformer Applications for Histopathological Image Analysis: New Developments and Future Directions // Biomedical Engineering Online. 2023. Vol. 22, No. 1. https://doi.org/10.1186/s12938-023-01069-5
4. Azad R., Kazerouni A., Heidari M., et al. Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review // arXiv. 2023.
5. Shamshad F., Khan S., Zamir S.W., et al. Transformers in Medical Imaging: A Survey // Medical Image Analysis. 2024. Vol. 88. https://doi.org/10.1016/j.media.2023.102843
6. Liu Y., et al. A Recent Survey of Vision Transformers for Medical Image Segmentation // arXiv. 2023.
7. Wu F., et al. Lite Transformer with Long-Short Range Attention // Proceedings of the International Conference on Learning Representations (ICLR). 2020.
8. Jacob B., et al. Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018. P. 2704–2713. https://doi.org/10.1109/CVPR.2018.00286
9. Nagel M., et al. A White Paper on Neural Network Quantization // arXiv. 2021.
10. Han S., Mao H., Dally W.J. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding // arXiv. 2016.
11. Yao Z., et al. ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers // Advances in Neural Information Processing Systems (NeurIPS). 2022. Vol. 35.
12. Wikipedia contributors. Model Compression // Wikipedia. 2025.
13. Hinton G., Vinyals O., Dean J. Distilling the Knowledge in a Neural Network // arXiv. 2015.
14. Gou J., et al. Knowledge Distillation: A Survey // International Journal of Computer Vision. 2021. Vol. 129, No. 6. P. 1789–1819.https://doi.org/10.1007/s11263-021-01453-z
15. Umirzakova S., et al. Simplified Knowledge Distillation for Deep Neural Networks: Bridging the Performance Gap with a Novel Teacher–Student Architecture // Electronics. 2024. Vol. 13, No. 3. https://doi.org/10.3390/electronics13030512
16. Liang P., et al. Data-Free Knowledge Distillation with Feature Synthesis and Spatial Consistency for Image Analysis // Scientific Reports. 2024. Vol. 14, No. 1. https://doi.org/10.1038/s41598-024-53241-3
This work is licensed under a Creative Commons Attribution 4.0 International License.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.