A Quantization-Friendly Separable Convolution for MobileNets
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
As deep learning (DL) is being rapidly pushed to edge computing, researchers invented various ways to make inference computation more efficient on mobile/IoT devices, such as network pruning, parameter compression, and etc. Quantization, as one of the key approaches, can effectively offload GPU, and make it possible to deploy DL on fixed-point pipeline. Unfortunately, not all existing networks design are friendly to quantization. For example, the popular lightweight MobileNetV1, while it successfully reduces parameter size and computation latency with separable convolution, our experiment shows its quantized models have large performance gap against its float point models. To resolve this, we analyzed the root cause of quantization loss and proposed a quantization-friendly separable convolution architecture. By evaluating the image classification task on ImageNet2012 dataset, our modified MobileNetV1 model can archive 8-bit inference top-1 accuracy in 68.03%, almost closed the gap to the float pipeline.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1707.01083 · Cited by 9,982
Self-citationShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00716 · Cited by 9,982
Self-citationQuantization 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
Cited by
Pruning and quantization for deep neural network acceleration: A survey
Liang, T., Glossner, J., Wang, L., Shi, S., & Zhang, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.045 · Cited by 943
Self-citationData-Free Quantization Through Weight Equalization and Bias Correction
Nagel, M., Baalen, M. V., Blankevoort, T., & Welling, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00141 · Cited by 500
AI Benchmark: Running Deep Neural Networks on Android Smartphones
Ignatov, A., Timofte, R., Chou, W., Wang, K., Wu, M., Hartley, T., & Van Gool, L. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-11021-5_19 · Cited by 347
A White Paper on Neural Network Quantization
Nagel, M., Fournarakis, M., Amjad, R. A., Bondarenko, Y., van Baalen, M., & Blankevoort, T. (2021) · arXiv · doi:10.48550/arxiv.2106.08295 · Cited by 323
Fdftnet: facing off fake images using fake detection fine-tuning network
Jeon, H., Bang, Y., & Woo, S. S. (2020) · IFIP Advances in Information and Communication Technology · doi:10.1007/978-3-030-58201-2_28 · Cited by 65
“Since clipping the input values at the bottom layers may have a side effect of distorting the data distribution [26], we apply these activation functions at the top layers to reduce distortion and extract different signals from ReLU.”
MethodSame, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization
Meller, E., Finkelstein, A., Almog, U., & Grobman, M. (2019) · arXiv · doi:10.48550/arxiv.1902.01917 · Cited by 60
“Used in conjunction with equalization we get competitive results (Table 2) with the state-of-the art (Jacob et al., 2017; Lee et al., 2018; Krishnamoorthi, 2018; Sheng et al., 2018; Google).”
BackgroundMethodInfluentialMake RepVGG Greater Again: A Quantization-aware Approach
Chu, X., Li, L., & Zhang, B. (2022) · arXiv · doi:10.48550/arxiv.2212.01593 · Cited by 53
Bit Efficient Quantization for Deep Neural Networks
Nayak, P., Zhang, D., & Chai, S. (2019) · 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS) · doi:10.1109/emc2-nips53020.2019.00020 · Cited by 51
Bit Efficient Quantization for Deep Neural Networks
Nayak, P., Zhang, D., & Chai, S. (2019) · arXiv · doi:10.48550/arxiv.1910.04877 · Cited by 51
Fighting Quantization Bias With Bias
Finkelstein, A., Almog, U., & Grobman, M. (2019) · arXiv · doi:10.48550/arxiv.1906.03193 · Cited by 41
Make RepVGG Greater Again: A Quantization-Aware Approach
Chu, X., Li, L., & Zhang, B. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i10.29045 · Cited by 53
Metadata
- Authors
- Sheng, T., Feng, C., Zhuo, S., Zhang, X., Shen, L., & Aleksic, M.
- Venue
- 2018 1st Workshop on Energy Efficient Machine Learning and Cognitive Computing for Embedded Applications (EMC2)
- Publisher
- IEEE
- Published
- 2018-03
- Pages
- 14-18
- OpenAlex
- W2790621718
- Cited by
- 76
- References
- 4
- FWCI
- 3.00
- Type
- conference paper
- Language
- en
- Open access
- green
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
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.