Abstract
Quantizing is a promising approach to facilitate deploying deep neural networks on resource-limited devices. However, existing methods are challenged by obtaining computation acceleration and parameter compression while maintaining excellent performance. To achieve this goal, we propose PSE, a mixed quantization framework which combines product quantization (PQ), scalar quantization (SQ), and error correction. Specifically, we first employ PQ to obtain the floating-point codebook and index matrix of the weight matrix. Then, we use SQ to quantize the codebook into integers and reconstruct an integer weight matrix. Finally, we propose an error correction algorithm to update the quantized codebook and minimize the quantization error. We extensively evaluate our proposed method on various backbones, including VGG-16, ResNet-18/50, MobileNetV2, ShuffleNetV2, EfficientNet-B3/B7, and DenseNet-201 on CIFAR-10 and ILSVRC-2012 benchmarks. The experiments demonstrate that PSE reduces computation complexity and model size with acceptable accuracy loss. For example, ResNet-18 achieves 1.8\(\times\) acceleration ratio and 30.4\(\times\) compression ratio with less than 1.54% accuracy loss on CIFAR-10.
Similar content being viewed by others
References
Bucila, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: KDD ’06 (2006)
Cai, Y., Yao, Z., Dong, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: Zeroq: a novel zero shot quantization framework. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13169–13178 (2020)
Chen, J., Bai, S., Huang, T., Wang, M., Tian, G., Liu, Y.: Data-free quantization via mixed-precision compensation without fine-tuning. Pattern Recognit. 143, 109780 (2023)
Chen, J., Liu, L., Liu, Y., Zeng, X.: A learning framework for n-bit quantized neural networks toward fpgas. IEEE Trans. Neural Netw. Learn. Syst. 32(3), 1067–1081 (2021). https://doi.org/10.1109/TNNLS.2020.2980041
Chen, T., Du, Z., Sun, N., Wang, J., Wu, C., Chen, Y., Temam, O.: Diannao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. in: Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems (2014)
Codrescu, L., Anderson, W., Venkumanhanti, S., Zeng, M., Plondke, E., Koob, C., Ingle, A., Tabony, C., Maule, R.: Hexagon dsp: an architecture optimized for mobile multimedia and communications. IEEE Micro 34(2), 34–43 (2014). https://doi.org/10.1109/MM.2014.12
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)
Dettmers, T.: 8-bit approximations for parallelism in deep learning. arXiv preprint arXiv:1511.04561 (2015)
Fan, A., Stock, P., Graham, B., Grave, E., Gribonval, R., Jegou, H., Joulin, A.: Training with quantization noise for extreme model compression. arXiv preprint arXiv:2004.07320 (2020)
Fan, J., Pan, Z., Wang, L., Wang, Y.: Codebook-softened product quantization for high accuracy approximate nearest neighbor search. Neurocomputing 507, 107–116 (2022)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In: International Conference on machine Learning, pp. 1050–1059. PMLR (2016)
Ge, T., He, K., Ke, Q., Sun, J.: Optimized product quantization for approximate nearest neighbor search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)
Gong, Y., Liu, L., Yang, M., Bourdev, L.: Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115 (2014)
Gupta, S., Agrawal, A., Gopalakrishnan, K., Narayanan, P.: Deep learning with limited numerical precision. In: Bach, F., Blei, D. (eds.) Rroceedings of the 32nd International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. 37, pp. 1737–1746. PMLR, Lille (2015)
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M., Dally, W.J.: Eie: Efficient inference engine on compressed deep neural network. 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) pp. 243–254 (2016)
Han, S., Mao, H., Dally, W.J.: Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. Vision and Pattern Recognition. arXiv: Computer (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. ArXiv abs/1503.02531 (2015)
Hong, W., Chen, T., Lu, M., Pu, S., Ma, Z.: Efficient neural image decoding via fixed-point inference. IEEE Trans. Circuits Syst. Video Technol. 31(9), 3618–3630 (2021). https://doi.org/10.1109/TCSVT.2020.3040367
Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Hu, B., Zhou, S., Xiong, Z., Wu, F.: Cross-resolution distillation for efficient 3D medical image registration. IEEE Trans. Circuits Syst. Video Technol. 32(10), 7269–7283 (2022). https://doi.org/10.1109/TCSVT.2022.3178178
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., Kalenichenko, D.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704–2713 (2018)
Jin, Q., Ren, J., Zhuang, R., Hanumante, S., Li, Z., Chen, Z., Wang, Y., Yang, K., Tulyakov, S.: F8net: Fixed-point 8-bit only multiplication for network quantization. arXiv preprint arXiv:2202.05239 (2022)
Jégou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117–128 (2011). https://doi.org/10.1109/TPAMI.2010.57
Krishnamoorthi, R.: Quantizing deep convolutional networks for efficient inference: a whitepaper. arXiv preprint arXiv:1806.08342 (2018)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. (2009)
Li, F., Zhang, B., Liu, B.: Ternary weight networks. arXiv preprint arXiv:1605.04711 (2016)
Li, Z., Sun, Y., Tian, G., Xie, L., Liu, Y., Su, H., He, Y.: A compression pipeline for one-stage object detection model. J. Real-Time Image Process. 18, 1949–1962 (2021)
Liang, T., Glossner, J., Wang, L., Shi, S., Zhang, X.: Pruning and quantization for deep neural network acceleration: a survey. Neurocomputing 461, 370–403 (2021)
Lin, J., Chen, W.M., Lin, Y., Cohn, J., Gan, C., Han, S.: Mcunet: tiny deep learning on IoT devices. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 11711–11722. Curran Associates Inc (2020)
Liu, C., Ding, W., Chen, P., Zhuang, B., Wang, Y., Zhao, Y., Zhang, B., Han, Y.: Rb-net: training highly accurate and efficient binary neural networks with reshaped point-wise convolution and balanced activation. IEEE Trans. Circuits Syst. Video Technol. 32(9), 6414–6424 (2022). https://doi.org/10.1109/TCSVT.2022.3166803
Liu, Y., Wu, D., Zhou, W., Fan, K., Zhou, Z.: Eacp: an effective automatic channel pruning for neural networks. Neurocomputing 526, 131–142 (2023)
Liu, Y., Wu, D., Zhou, W., Fan, K., Zhou, Z.: Eacp: an effective automatic channel pruning for neural networks. Neurocomputing 526, 131–142 (2023). https://doi.org/10.1016/j.neucom.2023.01.014
Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., Cheng, K.: Bi-real net: enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm. In: ECCV (2018)
Ma, N., Zhang, X., Zheng, H.T., Sun, J.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116–131 (2018)
Nguyen, D.T., Kim, H., Lee, H.J.: Layer-specific optimization for mixed data flow with mixed precision in FPGA design for CNN-based object detectors. IEEE Trans. Circuits Syst. Video Technol. 31(6), 2450–2464 (2021). https://doi.org/10.1109/TCSVT.2020.3020569
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural. Inf. Process. Syst. 32, 8026–8037 (2019)
Patel, G., Mopuri, K.R., Qiu, Q.: Learning to retain while acquiring: combating distribution-shift in adversarial data-free knowledge distillation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7786–7794 (2023)
Qiu, J., Wang, J., Yao, S., Guo, K., Li, B., Zhou, E., Yu, J., Tang, T., Xu, N., Song, S., Wang, Y., Yang, H.: Going deeper with embedded fpga platform for convolutional neural network. In: Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (2016)
Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: Xnor-net: Imagenet classification using binary convolutional neural networks. In: European Conference on Computer Vision, pp. 525–542. Springer (2016)
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Sayed, R., Azmi, H., Shawkey, H., Khalil, A.H., Refky, M.: A systematic literature review on binary neural networks. IEEE Access 11, 27546–27578 (2023). https://doi.org/10.1109/ACCESS.2023.3258360
Shang, Y., Xu, D., Zong, Z., Nie, L., Yan, Y.: Network binarization via contrastive learning. In: European Conference on Computer Vision, pp. 586–602. Springer (2022)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Stock, P., Joulin, A., Gribonval, R., Graham, B., Jégou, H.: And the bit goes down: Revisiting the quantization of neural networks. arXiv preprint arXiv:1907.05686 (2019)
Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)
Tian, G., Chen, J., Zeng, X., Liu, Y.: Pruning by training: a novel deep neural network compression framework for image processing. IEEE Signal Process. Lett. 28, 344–348 (2021)
Tu, Z., Chen, X., Ren, P., Wang, Y.: Adabin: improving binary neural networks with adaptive binary sets. In: European conference on computer vision, pp. 379–395. Springer (2022)
Vanhoucke, V., Senior, A., Mao, M.Z.: Improving the speed of neural networks on cpus (2011)
Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: Haq: Hardware-aware automated quantization with mixed precision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Wang, Z., Xiao, H., Lu, J., Zhou, J.: Generalizable mixed-precision quantization via attribution rank preservation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5291–5300 (2021)
Wu, J., Leng, C., Wang, Y., Hu, Q., Cheng, J.: Quantized convolutional neural networks for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4820–4828 (2016)
Xu, Z., Lin, M., Liu, J., Chen, J., Shao, L., Gao, Y., Tian, Y., Ji, R.: Recu: Reviving the dead weights in binary neural networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5198–5208 (2021)
Yang, C., Liu, H.: Channel pruning based on convolutional neural network sensitivity. Neurocomputing 507, 97–106 (2022)
Zhang, D., Yang, J., Ye, D., Hua, G.: Lq-nets: Learned quantization for highly accurate and compact deep neural networks. ArXiv abs/1807.10029 (2018)
Zhang, J., Su, Z., Feng, Y., Lu, X., Pietikäinen, M., Liu, L.: Dynamic binary neural network by learning channel-wise thresholds. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1885–1889. IEEE (2022)
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)
Zhou, A., Yao, A., Guo, Y., Xu, L., Chen, Y.: Incremental network quantization: Towards lossless CNNS with low-precision weights. arXiv preprint arXiv:1702.03044 (2017)
Zhuang, B., Shen, C., Tan, M., Liu, L., Reid, I.D.: Towards effective low-bitwidth convolutional neural networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 7920–7928 (2018)
Acknowledgements
This work is supported in part by the National Natural Science Foundation of China under Grant 62303405, in part by Ningbo Natural Science Foundation project under Grant 2023J400, and in part by Zhejiang Provincial Basic Public Welfare Research Project of China under Grant No. LGG22F030019.
Author information
Authors and Affiliations
Contributions
YY: Conceptualization, Software, Validation, Formal analysis, Data Curation, Writing - Original Draft, Writing-Review and Editing, Visualization. GT: Resources, Supervision, Project administration, Funding acquisition. ML: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data Curation, Project administration. YC: Writing-Review and Editing. JC: Conceptualization, Writing-Review and Editing. LM: Resources, Funding acquisition. YL: Resources, Funding acquisition. YP: Resources, Funding acquisition. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yang, Y., Tian, G., Liu, M. et al. Pse: mixed quantization framework of neural networks for efficient deployment. J Real-Time Image Proc 20, 113 (2023). https://doi.org/10.1007/s11554-023-01366-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11554-023-01366-9