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.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Since AdaHessian is very memory expensive, we can only give partial results in the following experiments.
- 2.
These models for CIFAR100/10 can be downloaded at the repository https://github.com/weiaicunzai/pytorch-cifar100.
- 3.
- 4.
References
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)
Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)
Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(Jul), 2121–2159 (2011)
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)
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)
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)
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)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
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)
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)
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)
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)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
Lei Ba, J., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
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)
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, L., et al.: On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265 (2019)
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)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
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)
Ma, X.: Apollo: an adaptive parameter-wise diagonal quasi-newton method for nonconvex stochastic optimization. arXiv preprint arXiv:2009.13586 (2020)
Martens, J., Grosse, R.: Optimizing neural networks with kronecker-factored approximate curvature. In: International Conference on Machine Learning, pp. 2408–2417. PMLR (2015)
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)
Pascanu, R., Mikolov, T., Bengio, Y.: Understanding the exploding gradient problem. CoRR, abs/1211.5063, vol. 2 (2012)
Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: International Conference on Machine Learning, pp. 1310–1318 (2013)
Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145–151 (1999)
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)
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
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Santurkar, S., Tsipras, D., Ilyas, A., Madry, A.: How does batch normalization help optimization? In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Siarohin, A., Sangineto, E., Sebe, N.: Whitening and coloring batch transform for gans. arXiv preprint arXiv:1806.00420 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Teye, M., Azizpour, H., Smith, K.: Bayesian uncertainty estimation for batch normalized deep networks. arXiv preprint arXiv:1802.06455 (2018)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)
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
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)
Ye, C., et al.: Network deconvolution. arXiv preprint arXiv:1905.11926 (2019)
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
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
Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)
Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530 (2016)
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)
Zhang, M.R., Lucas, J., Hinton, G., Ba, J.: Lookahead optimizer: k steps forward, 1 step back. arXiv preprint arXiv:1907.08610 (2019)
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)
Zhuang, J., et al.: Adabelief optimizer: adapting stepsizes by the belief in observed gradients. arXiv preprint arXiv:2010.07468 (2020)
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
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)