Skip to main content
SpringerLink
Log in

An Embedded Feature Whitening Approach to Deep Neural Network Optimization

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13683))

Included in the following conference series:

Abstract

Compared with the feature normalization methods that are widely used in deep neural network (DNN) training, feature whitening methods take the correlation of features into consideration, which can help to learn more effective features. However, existing feature whitening methods have several limitations, such as the large computation and memory cost, inapplicable to pre-trained DNN models, the introduction of additional parameters, etc., making them impractical to use in optimizing DNNs. To overcome these drawbacks, we propose a novel Embedded Feature Whitening (EFW) approach to DNN optimization. EFW only adjusts the gradient of weight by using the whitening matrix without changing any part of the network so that it can be easily adopted to optimize pre-trained and well-defined DNN architectures. The momentum, adaptive dampening and gradient norm recovery techniques associated with EFW are consequently developed to make its implementation efficient with acceptable extra computation and memory cost. We apply EFW to two commonly used DNN optimizers, i.e., SGDM and Adam (or AdamW), and name the obtained optimizers as W-SGDM and W-Adam. Extensive experimental results on various vision tasks, including image classification, object detection, segmentation and person ReID, demonstrate the superiority of W-SGDM and W-Adam to state-of-the-art DNN optimizers. The code are publicly available at https://github.com/Yonghongwei/W-SGDM-and-W-Adam.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Since AdaHessian is very memory expensive, we can only give partial results in the following experiments.

  2. 2.

    These models for CIFAR100/10 can be downloaded at the repository https://github.com/weiaicunzai/pytorch-cifar100.

  3. 3.

    https://github.com/open-mmlab/mmdetection.

  4. 4.

    https://github.com/michuanhaohao/reid-strong-baseline.

References

  1. Chen, J., Zhou, D., Tang, Y., Yang, Z., Cao, Y., Gu, Q.: Closing the generalization gap of adaptive gradient methods in training deep neural networks. arXiv preprint arXiv:1806.06763 (2018)

  2. Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)

  3. Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(Jul), 2121–2159 (2011)

    Google Scholar 

  4. Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)

    Google Scholar 

  5. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)

    Google Scholar 

  6. He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)

    Google Scholar 

  7. 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)

    Google Scholar 

  8. Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)

  9. 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)

    Google Scholar 

  10. Huang, L., Yang, D., Lang, B., Deng, J.: Decorrelated batch normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 791–800 (2018)

    Google Scholar 

  11. Huang, L., Zhou, Y., Zhu, F., Liu, L., Shao, L.: Iterative normalization: beyond standardization towards efficient whitening. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4874–4883 (2019)

    Google Scholar 

  12. Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501–1510 (2017)

    Google Scholar 

  13. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)

  14. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  15. Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)

    Google Scholar 

  16. Lei Ba, J., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)

  17. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

    Google Scholar 

  18. 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

    Chapter  Google Scholar 

  19. Liu, L., et al.: On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265 (2019)

  20. Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)

    Google Scholar 

  21. Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)

  22. Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)

    Google Scholar 

  23. Ma, X.: Apollo: an adaptive parameter-wise diagonal quasi-newton method for nonconvex stochastic optimization. arXiv preprint arXiv:2009.13586 (2020)

  24. Martens, J., Grosse, R.: Optimizing neural networks with kronecker-factored approximate curvature. In: International Conference on Machine Learning, pp. 2408–2417. PMLR (2015)

    Google Scholar 

  25. Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 807–814 (2010)

    Google Scholar 

  26. Pascanu, R., Mikolov, T., Bengio, Y.: Understanding the exploding gradient problem. CoRR, abs/1211.5063, vol. 2 (2012)

    Google Scholar 

  27. Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: International Conference on Machine Learning, pp. 1310–1318 (2013)

    Google Scholar 

  28. Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145–151 (1999)

    Article  Google Scholar 

  29. 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)

    Google Scholar 

  30. Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17–35. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_2

    Chapter  Google Scholar 

  31. Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)

    Article  MathSciNet  Google Scholar 

  32. Santurkar, S., Tsipras, D., Ilyas, A., Madry, A.: How does batch normalization help optimization? In: Advances in Neural Information Processing Systems, vol. 31 (2018)

    Google Scholar 

  33. Siarohin, A., Sangineto, E., Sebe, N.: Whitening and coloring batch transform for gans. arXiv preprint arXiv:1806.00420 (2018)

  34. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

  35. Teye, M., Azizpour, H., Smith, K.: Bayesian uncertainty estimation for batch normalized deep networks. arXiv preprint arXiv:1802.06455 (2018)

  36. Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)

  37. Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_1

    Chapter  Google Scholar 

  38. Yao, Z., Gholami, A., Shen, S., Mustafa, M., Keutzer, K., Mahoney, M.W.: Adahessian: an adaptive second order optimizer for machine learning. arXiv preprint arXiv:2006.00719 (2020)

  39. Ye, C., et al.: Network deconvolution. arXiv preprint arXiv:1905.11926 (2019)

  40. Yong, H., Huang, J., Hua, X., Zhang, L.: Gradient centralization: a new optimization technique for deep neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 635–652. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_37

    Chapter  Google Scholar 

  41. Yong, H., Huang, J., Meng, D., Hua, X., Zhang, L.: Momentum batch normalization for deep learning with small batch size. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 224–240. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_14

    Chapter  Google Scholar 

  42. Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)

  43. Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530 (2016)

  44. Zhang, H., Chen, W., Liu, T.Y.: Train feedfoward neural network with layer-wise adaptive rate via approximating back-matching propagation. arXiv preprint arXiv:1802.09750 (2018)

  45. Zhang, M.R., Lucas, J., Hinton, G., Ba, J.: Lookahead optimizer: k steps forward, 1 step back. arXiv preprint arXiv:1907.08610 (2019)

  46. Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)

    Google Scholar 

  47. Zhuang, J., et al.: Adabelief optimizer: adapting stepsizes by the belief in observed gradients. arXiv preprint arXiv:2010.07468 (2020)

Download references

Author information

Authors and Affiliations

  1. The Hong Kong Polytechnic University, Hong Kong, China

    Hongwei Yong & Lei Zhang

Authors
  1. Hongwei Yong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lei Zhang .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 287 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Yong, H., Zhang, L. (2022). An Embedded Feature Whitening Approach to Deep Neural Network Optimization. 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 13683. Springer, Cham. https://doi.org/10.1007/978-3-031-20050-2_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20050-2_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20049-6

  • Online ISBN: 978-3-031-20050-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation