Abstract
With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream tasks. However, we find that current SSL models suffer severe accuracy drops when performing low-bit quantization, prohibiting their deployment in resource-constrained applications. In this paper, we propose a method called synergistic self-supervised and quantization learning (SSQL) to pretrain quantization-friendly self-supervised models facilitating downstream deployment. SSQL contrasts the features of the quantized and full precision models in a self-supervised fashion, where the bit-width for the quantized model is randomly selected in each step. SSQL not only significantly improves the accuracy when quantized to lower bit-widths, but also boosts the accuracy of full precision models in most cases. By only training once, SSQL can then benefit various downstream tasks at different bit-widths simultaneously. Moreover, the bit-width flexibility is achieved without additional storage overhead, requiring only one copy of weights during training and inference. We theoretically analyze the optimization process of SSQL, and conduct exhaustive experiments on various benchmarks to further demonstrate the effectiveness of our method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bengio, Y., Léonard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)
Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: The European Conference on Computer Vision. LNCS, vol. 11218, pp. 132–149. Springer, Cham (2018)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems, pp. 9912–9924 (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: The International Conference on Machine Learning, pp. 1597–1607 (2020)
Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)
Chen, X., He, K.: Exploring simple Siamese representation learning. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 15750–15758 (2021)
Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I.J., Srinivasan, V., Gopalakrishnan, K.: PACT: parameterized clipping activation for quantized neural networks. In: The International Conference on Learning Representations, pp. 1–12 (2018)
Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representations learning by context prediction. In: The IEEE International Conference on Computer Vision, pp. 1422–1430 (2015)
Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.S.: Learned step size quantization. In: The International Conference on Learning Representations, pp. 1–12 (2020)
Everingham, M., Gool, L.V., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Fang, Z., Wang, J., Wang, L., Zhang, L., Yang, Y., Liu, Z.: SEED: self-supervised distillation for visual representation. In: The International Conference on Learning Representations, pp. 1–12 (2021)
Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: The International Conference on Learning Representations, pp. 1–14 (2015)
Grill, J.B., et al.: Boostrap your own latent: a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, pp. 21271–21284 (2020)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In: The International Conference on Learning Representations, pp. 1–14 (2016)
Han, T., Li, D., Liu, J., Tian, L., Shan, Y.: Improving low-precision network quantization via bin regularization. In: The IEEE International Conference on Computer Vision, pp. 5261–5270 (2021)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 9729–9738 (2020)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: The IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Hubara, I., Nahshan, Y., Hanani, Y., Banner, R., Soudry, D.: Accurate post training quantization with small calibration sets. In: The International Conference on Machine Learning, pp. 4466–4475 (2021)
Jin, Q., Yang, L., Liao, Z.: AdaBits: neural network quantization with adaptive bit-widths. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 2146–2156 (2020)
Krizhevsky, A., Hinton, G.E.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)
Li, Y., et al.: BRECQ: pushing the limit of post-training quantization by block reconstruction. In: The International Conference on Learning Representations, pp. 1–16 (2021)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 2177–2125 (2017)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, X., et al.: Self-supervised learning: generative or contrastive. arXiv preprint arXiv:2006.08218 (2020)
Luo, J.H., Wu, J., Lin, W.: ThiNet: a filter level pruning method for deep neural network compression. In: The IEEE International Conference on Computer Vision, pp. 5058–5066 (2017)
van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(86), 2579–2605 (2008)
Nagel, M., Amjad, R.A., van Baalen, M., Louizos, C., Blankevoort, T.: Up or down? Adaptive rounding for post-training quantization. In: The International Conference on Machine Learning, pp. 7197–7206 (2020)
Nagel, M., van Baalen, M., Blankevoort, T., Welling, M.: Data-free quantization through weight equalization and bias correction. In: The IEEE International Conference on Computer Vision, pp. 1325–1334 (2019)
Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69–84. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_5
van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Shen, M., et al.: Once quantization-aware training: high performance extremely low-bit architecture search. In: The IEEE International Conference on Computer Vision, pp. 5340–5349 (2021)
Shen, Z., Liu, Z., Qin, J., Huang, L., Cheng, K.T., Savvides, M.: S2-BNN: bridging the gap between self-supervised real and 1-bit neural networks via guided distribution calibration. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 2165–2173 (2021)
Sheng, T., Feng, C., Zhuo, S., Zhang, X., Shen, L., Aleksic, M.: A quantization-friendly separable convolution for mobilenets. arXiv preprint arXiv:1803.08607 (2018)
Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). www.github.com/facebookresearch/detectron2
Yu, H., Wen, T., Cheng, G., Sun, J., Han, Q., Shi, J.: Low-bit quantization needs good distribution. In: The IEEE Conference on Computer Vision and Pattern Recognition Workshops (2020)
Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649–666. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_40
Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cao, YH., Sun, P., Huang, Y., Wu, J., Zhou, S. (2022). Synergistic Self-supervised and Quantization Learning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13690. Springer, Cham. https://doi.org/10.1007/978-3-031-20056-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-20056-4_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20055-7
Online ISBN: 978-3-031-20056-4
eBook Packages: Computer ScienceComputer Science (R0)