Abstract
We revisit the benefits of merging classical vision concepts with deep learning models. In particular, we explore the effect of replacing the first layers of various deep architectures with Gabor layers (i.e. convolutional layers with filters that are based on learnable Gabor parameters) on robustness against adversarial attacks. We observe that architectures with Gabor layers gain a consistent boost in robustness over regular models and maintain high generalizing test performance. We then exploit the analytical expression of Gabor filters to derive a compact expression for a Lipschitz constant of such filters, and harness this theoretical result to develop a regularizer we use during training to further enhance network robustness. We conduct extensive experiments with various architectures (LeNet, AlexNet, VGG16, and WideResNet) on several datasets (MNIST, SVHN, CIFAR10 and CIFAR100) and demonstrate large empirical robustness gains. Furthermore, we experimentally show how our regularizer provides consistent robustness improvements.
J. C. Perez, M. Alfarra, G. Jeanneret denotes equal contribution.
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
Notes
References
Alekseev, A., Bobe, A.: Gabornet: gabor filters with learnable parameters in deep convolutional neural network. In: International Conference on Engineering and Telecommunication (EnT) (2019)
Atanov, A., Ashukha, A., Struminsky, K., Vetrov, D., Welling, M.: The deep weight prior. In: International Conference on Learning Representations (ICLR) (2019)
Bai, M., Urtasun, R.: Deep watershed transform for instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Bibi, A., Ghanem, B., Koltun, V., Ranftl, R.: Deep layers as stochastic solvers. In: International Conference on Learning Representations (ICLR) (2019)
Cao, Y., et al.: Adversarial sensor attack on lidar-based perception in autonomous driving. In: ACM SIGSAC Conference on Computer and Communications Security (2019)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: IEEE Symposium on Security and Privacy (SP) (2017)
Chen, Y., Zhu, L., Ghamisi, P., Jia, X., Li, G., Tang, L.: Hyperspectral images classification with gabor filtering and convolutional neural network. IEEE Geosci. Remote Sens. Lett. 14, 2355–2359 (2017)
Liu, C., Wechsler, H.: Independent component analysis of gabor features for face recognition. IEEE Trans. Neural Netw. 14, 919–928 (2003)
Chernikova, A., Oprea, A., Nita-Rotaru, C., Kim, B.: Are self-driving cars secure? evasion attacks against deep neural networks for steering angle prediction. In: IEEE Security and Privacy Workshops (SPW) (2019)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Cisse, M., Bojanowski, P., Grave, E., Dauphin, Y., Usunier, N.: Parseval networks: improving robustness to adversarial examples. In: International Conference on Machine Learning (ICML) (2017)
Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1915–1929 (2012)
Gabor, D.: Theory of communication. Part 1: The analysis of information. J. Inst. Electr. Eng. Part III Radio Commun. Eng. 93, 429–441 (1946)
Goldstein, T., Osher, S.: The split Bregman method for L1-regularized problems. SIAM J. Imag. Sci. 2, 323–343 (2009)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (ICLR) (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Patter Recognition (CVPR) (2016)
Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29, 82–97 (2012)
Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurons in the cat’s striate cortex. J. Physiol. 148, 574–591 (1959)
Julesz, B.: Textons, the elements of texture perception, and their interactions. Nature 290, 91–97 (1981)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems (NeurIPS) (2012)
LeCun, Y.: The MNIST database of handwritten digits (1998). http://yann.lecun.com/exdb/mnist/
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
LeCun, Y., Haffner, P., Bottou, L., Bengio, Y.: Object recognition with gradient-based learning. Shape, Contour and Grouping in Computer Vision. LNCS, vol. 1681, pp. 319–345. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-46805-6_19
Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. Int. J. Comput. Vis. (IJCV) 43, 29–44 (2001)
Lowe, D.G.: Object recognition from local scale-invariant features. In: International Conference on Computer Vision (ICCV). IEEE (1999)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. (IJCV) 60, 91–110 (2004)
Luan, S., Chen, C., Zhang, B., Han, J., Liu, J.: Gabor convolutional networks. IEEE Trans. Image Process. 27, 4357–4366 (2018)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: International Conference on Learning Representations (ICLR) (2018)
Marr, D.: Vision: a computational investigation into the human representation and processing of visual information. In: PsycCRITIQUES (1982)
Montufar, G., Pascanu, R., Cho, K., Bengio, Y.: On the number of linear regions of deep neural networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2014)
Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.: Deepfool: a simple and accurate method to fool deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Namuduri, K.R., Mehrotra, R., Ranganathan, N.: Edge detection models based on Gabor filters. In: International Conference on Pattern Recognition. Conference C: Image, Speech and Signal Analysis (1992)
Novak, C.L., Shafer, S.A., et al.: Anatomy of a color histogram. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (1992)
Ouyang, W., Wang, X.: Joint deep learning for pedestrian detection. In: IEEE International Conference on Computer Vision (ICCV) (2013)
Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: IEEE Symposium on Security and Privacy (SP) (2016)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12, 629–639 (1990)
Poggi, M., Mattoccia, S.: A wearable mobility aid for the visually impaired based on embedded 3D vision and deep learning. In: 2016 IEEE Symposium on Computers and Communication (ISCC) (2016)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. In: International Journal of Computer Vision (IJCV) (2015)
Sarwar, S.S., Panda, P., Roy, K.: Gabor filter assisted energy efficient fast learning convolutional neural networks. CoRR (2017)
Sedghi, H., Gupta, V., Long, P.M.: The singular values of convolutional layers. In: International Conference on Learning Representations (ICLR) (2019)
Shafahi, A., et al.: Adversarial training for free! In: Neural Information Processing Systems (NeurIPS) (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)
Su, Y.M., Wang, J.F.: A novel stroke extraction method for Chinese characters using Gabor filters. Pattern Recogn. 36, 635–647 (2003)
Sun, J., Li, H., Xu, Z., et al.: Deep ADMM-net for compressive sensing MRI. In: Neural Information Systems (NeurIPS) (2016)
Szegedy, C., et al.: Intriguing properties of neural networks. In: International Conference on Learning Representations (ICLR) (2014)
Wong, E., Rice, L., Kolter, J.Z.: Fast is better than free: revisiting adversarial training. In: International Conference on Learning Representations (ICLR) (2020)
Xu, K., et al.: Structured adversarial attack: towards general implementation and better interpretability. In: International Conference on Learning Representations (ICLR) (2019)
Yao, H., Chuyi, L., Dan, H., Weiyu, Y.: Gabor feature based convolutional neural network for object recognition in natural scene. In: International Conference on Information Science and Control Engineering (ICISCE) (2016)
Zagoruyko, S., Komodakis, N.: Wide residual networks. In: British Machine Vision Conference (BMVC) (2016)
Zhang, D., Zhang, T., Lu, Y., Zhu, Z., Dong, B.: You only propagate once: accelerating adversarial training via maximal principle. In: Neural Information Processing Systems (NeurIPS) (2019)
Zhang, J., Ghanem, B.: Deep learning. In: IEEE Conference on Computer Vision and Patter Recognition (CVPR) (2017)
Zhang, R.: Making convolutional networks shift-invariant again. In: International Con-ference on Machine Learning (ICML) (2019)
Zhong, Z., Jin, L., Xie, Z.: High performance offline handwritten Chinese character recognition using Googlenet and directional feature maps. In: International Conference on Document Analysis and Recognition (ICDAR) (2015)
Acknowledgements
This work was partially supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. OSR-CRG2019-4033.
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
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Pérez, J.C. et al. (2020). Gabor Layers Enhance Network Robustness. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12354. Springer, Cham. https://doi.org/10.1007/978-3-030-58545-7_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-58545-7_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58544-0
Online ISBN: 978-3-030-58545-7
eBook Packages: Computer ScienceComputer Science (R0)