The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Leveraging Automated Mixed-Low-Precision Quantization for Tiny Edge Microcontrollers
Open accessOverview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“To resolve this issue, (Rusci et al., 2020) presented the HAQ framework which is based on the automated mixed-precision quantization flow scheme.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The agent repeatedly (15 epochs) tries to learn the quantization policy and accuracy based on the given proxy dataset.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The HAQ framework is targeted to deploy deep neural networks in the tiny IoT-based devices, especially for the reinforcement learning agents (2, 4, 8 bits quantization levels).”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In the search phase, HAQ uses reinforcement learning agents to follow the given quantization policy.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The proxy dataset (subset of main dataset) is fed to the reinforcement learning agent for scoring accuracy and the same is returned back to the reward function.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“It works in twophases, (i) search and (ii) fine-tuning.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“One quantization policy is selected at a time by a reinforcement learning agent during a number of fixed episodes (300 number).”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“The fine-tuning phase updates the model parameters based on the quantization-aware training process.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“The HAQ selects the weight and activation bandwidth during the search phase along with memory constraints associated with the IoT device.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“While selecting the quantization levels, HAQ aims to optimize the individual weight and activation tensors for a given IoT-based device's memory and processing capability.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“The HAQ works on the concept of automated precision training to optimally select the quantization bandwidth.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Rusci et al., 2020
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
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
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00293 · Cited by 3,416
HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision
Dong, Z., Yao, Z., Gholami, A., Mahoney, M., & Keutzer, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00038 · Cited by 492
Research works printed but not linked: 20
- Banbury, C.R., et al.: Benchmarking tinyml systems: challenges and direction. arXiv preprint arXiv:2003.04821 (2020) · arXiv
- Bruschi, N., Garofalo, A., Conti, F., Tagliavini, G., Rossi, D.: Enabling mixed-precision quantized neural networks in extreme-edge devices. In: Proceedings of the 17th ACM International Conference on Computing Frontiers, pp. 217–220 (2020) · DOI
- Canziani, A., Paszke, A., Culurciello, E.: An analysis of deep neural network models for practical applications. arXiv preprint arXiv:1605.07678 (2016) · arXiv
- Capotondi, A., Rusci, M., Fariselli, M., Benini, L.: CMix-NN: mixed low-precision CNN library for memory-constrained edge devices. IEEE Trans. Circ. Syst. II: Express Briefs 67(5), 871–875 (2020)
- Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I.J., Srinivasan, V., Gopalakrishnan, K.: Pact: parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085 (2018) · arXiv
- Chowdhery, A., Warden, P., Shlens, J., Howard, A., Rhodes, R.: Visual wake words dataset. arXiv preprint arXiv:1906.05721 (2019) · arXiv
- Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: training deep neural networks with weights and activations constrained to +1 or $$-$$1. arXiv preprint arXiv:1602.02830 (2016) · arXiv
- Fedorov, I., Adams, R.P., Mattina, M., Whatmough, P.N.: Sparse: sparse architecture search for cnns on resource-constrained microcontrollers. arXiv preprint arXiv:1905.12107 (2019) · arXiv
- Flamand, E., et al.: Gap-8: a RISC-v SoC for AI at the edge of the IoT. In: 2018 IEEE 29th International Conference on Application-Specific Systems, Architectures and Processors (ASAP), pp. 1–4. IEEE (2018) · DOI
- Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017) · arXiv
- Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Advances in Neural Information Processing Systems, pp. 4107–4115 (2016)
- Krishnamoorthi, R.: Quantizing deep convolutional networks for efficient inference: a whitepaper. arXiv preprint arXiv:1806.08342 (2018) · arXiv
- Lai, L., Suda, N., Chandra, V.: CMSIS-NN: Efficient neural network kernels for arm cortex-m CPUs. arXiv preprint arXiv:1801.06601 (2018) · arXiv
- Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018) · arXiv
- Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525–542. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_32 · DOI · Paper page
- Rusci, M., Capotondi, A., Benini, L.: Memory-driven mixed low precision quantization for enabling deep network inference on microcontrollers. arXiv preprint arXiv:1905.13082 (2019) · arXiv
- Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018) · DOI · Paper page
- Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: Haq: hardware-aware automated quantization with mixed precision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019) · DOI · Paper page
- Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018) · DOI · Paper page
- Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: Dorefa-net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016) · arXiv
Cited by
Sorted by citations
A 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
“Recent work has shown that low precision and mixed-precision quantization with INT4/INT8 works in practice [51, 81, 101, 107, 182, 193, 204, 231, 238, 238, 241, 255, 259, 277].”
A review on TinyML: State-of-the-art and prospects
Ray, P. P. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.11.019 · Cited by 460
Metadata
- Authors
- Rusci, M., Fariselli, M., Capotondi, A., & Benini, L.
- Affiliations
- University of Bologna (IT)
- University of Modena and Reggio Emilia (IT)
- Corresponding author
- Rusci, Manuele
- Venue
- Communications in Computer and Information Science
- Publisher
- Springer International Publishing
- Published
- 2020
- Pages
- 296-308
- ISSN
- 1865-0929 (ISSN-L)
- 1865-0937
- OpenAlex
- W3048894487
- Cited by
- 27
- References
- 3
- Citations by year
- 2025: 7 · 2024: 1 · 2023: 5 · 2022: 10 · 2021: 3 · 2020: 1
- FWCI
- 1.47
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Communications in computer and information science (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna) (submittedVersion)
- IRIS UNIMORE (University of Modena and Reggio Emilia) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- mixed-precision quantization, uniform quantization, weight compression, MobileNet, embedded machine learning
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
