Benchmarking TensorFlow Lite Quantization Algorithms for Deep Neural Networks
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Deploying deep neural network models on the resource constrained devices, e.g., lost-cost microcontrollers, is challenging because they are mostly limited in terms of memory footprint and computation capabilities. Quantization is one of the widely used solutions to reduce the size of a model. For parameter representation, it employs for example just 8-bit integer or less instead of 32-bit floating point. The TensorFlow Lite deep learning framework currently provides four methods for post-training quantization. The aim of this paper is to benchmark these quantization methods using various deep neural models of different sizes. The main outcomes of the paper are: (1) the compression ratio obtained for each quantization method for deep neural models of small, medium, and large sizes, (2) a comparison of the accuracy results relative to the original accuracy, and (3) a viewpoint for the decision to choose the quantization method depending on the model size.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00286 · Cited by 4,114
Quantizing deep convolutional networks for efficient inference: A whitepaper
Krishnamoorthi, R. (2018) · arXiv · doi:10.48550/arxiv.1806.08342 · Cited by 753
What is the State of Neural Network Pruning?
Blalock, D., Ortiz, J. J. G., Frankle, J., & Guttag, J. (2020) · arXiv · doi:10.48550/arxiv.2003.03033 · Cited by 560
Edge Machine Learning for AI-Enabled IoT Devices: A Review
Merenda, M., Porcaro, C., & Iero, D. (2020) · Sensors · doi:10.3390/s20092533 · Cited by 523
TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems
David, R., Duke, J., Jain, A., Reddi, V. J., Jeffries, N., Li, J., Kreeger, N., Nappier, I., Natraj, M., Regev, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.08678 · Cited by 470
The Hardware and Algorithm Co-Design for Energy-Efficient DNN Processor on Edge/Mobile Devices
Lee, J., Kang, S., Lee, J., Shin, D., Han, D., & Yoo, H. (2020) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2020.3021397 · Cited by 68
Research works printed but not linked: 8
- Krishnamoorthi, 2018, Quantizing deepconvolutional networks for efficient inference: A whitepaper, arXiv
- Krizhevsky, 2022, The CIFAR-10 dataset
- 2022, Post-training dynamic range quantization
- 2022, Post-training integer quantization
- 2022, Post-training float16 quantization
- 2022, Post-training integer quantization with int16 activations
- Yuan, 2022, Training CIFAR-10 with TensorFlow2(TF2)
- 2022, X-CUBE-AI, AI expansion pack for STM32CubeMX
Cited by
Iqbal, U., Davies, T., & Perez, P. (2024) · Sensors · doi:10.3390/s24154830 · Cited by 77
Real-Time Stress Detection from Raw Noisy PPG Signals Using LSTM Model Leveraging TinyML
Rostami, A., Tarvirdizadeh, B., Alipour, K., & Ghamari, M. (2024) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-09095-2 · Cited by 27
Kristiani, E., Verma, V. K., & Chao-Tung, Y. (2026) · AI · doi:10.3390/ai7010015 · Cited by 26
Review of large YOLOv8 and RT-DETR energy efficiency on edge devices for real-time detection
Suchý, I., & Turčaník, M. (2026) · Scientific Reports · doi:10.1038/s41598-026-46453-6 · Cited by 14
Akhtar, M. H., Eksheir, I., & Shanableh, T. (2025) · Information · doi:10.3390/info16050348 · Cited by 10
Metadata
- Authors
- Orasan, I. L., Seiculescu, C., & Caleanu, C. D.
- Affiliations
- Politehnica University Timisoara,Faculty of Electronics, Telecommunications and Information Technologies,Departament of Applied Electronics,Timisoara,Romania
- Politehnica University of Timisoara (RO)
- Venue
- 2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)
- Publisher
- IEEE
- Published
- 2022-05-25
- Pages
- 000221-000226
- OpenAlex
- W4312857492
- Cited by
- 18
- References
- 18
- Citations by year
- 2026: 5 · 2025: 8 · 2024: 3 · 2023: 2
- FWCI
- 1.18
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Numerical Methods and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- TensorFlow Lite, post-training quantization, quantization algorithm, benchmarking, model compression, resource-constrained devices, embedded deep learning, model size, accuracy loss, microcontroller
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: Benchmarking TensorFlow Lite Quantization Algorithms for Deep Neural Networks. https://app.cochat.ai/papers/10.1109/saci55618.2022.9919465
- The paper
- Orasan, I. L., Seiculescu, C., & Caleanu, C. D. (2022). Benchmarking TensorFlow Lite Quantization Algorithms for Deep Neural Networks. 2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI). https://doi.org/10.1109/saci55618.2022.9919465
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.