Abstract
Knowledge distillation (KD) is a widely used model compression technology to train a superior small network named student network. KD promotes a student network to mimic the knowledge from the middle or deep layers of a large network named teacher network. In general, existing knowledge distillation methods neglect to explore the shallow features of neural networks that contain informative texture knowledge. In this paper, we propose Shallow Texture Knowledge Distillation (SeKD) for distilling these informative shallow features. Moreover, we investigate the traditional machine learning method and adopt Gradient Local Binary Pattern (GLBP) for shallow features extraction. However, we have found that using GLBP to process shallow features will introduce an additional computational burden. To reduce computation, we design a texture attention module to optimize shallow feature extraction for distilling. We have conducted extensive experiments to evaluate the effectiveness of our proposed method. When training on the CIFAR-10 and CIFAR-100 datasets, the student network WideResNet16-2 trained by SeKD achieves 94.35% and 75.90% accuracies, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bottou, L.: Stochastic gradient descent tricks. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 421–436. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_25
Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146–3154 (2019)
Heo, B., Lee, M., Yun, S., Choi, J.Y.: Knowledge transfer via distillation of activation boundaries formed by hidden neurons. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3779–3787 (2019)
Hinton, G., Vinyals, O., Dean, J., et al.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, vol. 2, no. 7 (2015)
Huang, Z., Wang, N.: Like what you like: knowledge distill via neuron selectivity transfer. arXiv preprint arXiv:1707.01219 (2017)
Jiang, N., Tang, J., Yu, W., Zhou, J., Mai, L.: Gradient local binary pattern layer to initialize the convolutional neural networks. In: 2021 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1–5. IEEE (2021)
Jiang, N., Xu, J., Goto, S.: Pedestrian detection using gradient local binary patterns. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 95(8), 1280–1287 (2012)
Jiang, N., Xu, J., Yu, W.: An intra-combined feature for pedestrian detection. IIEEJ Trans. Image Electron. Visual Comput. 1(1), 88–96 (2013)
Jiang, N., Xu, J., Yu, W., Goto, S.: Gradient local binary patterns for human detection. In: 2013 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 978–981. IEEE (2013)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Lee, S.H., Kim, D.H., Song, B.C.: Self-supervised knowledge distillation using singular value decomposition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 335–350 (2018)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)
Passalis, N., Tefas, A.: Probabilistic knowledge transfer for deep representation learning. CoRR, abs/1803.10837, vol. 1, no. 2, p. 5 (2018)
Polino, A., Pascanu, R., Alistarh, D.: Model compression via distillation and quantization. arXiv preprint arXiv:1802.05668 (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, vol. 28 (2015)
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)
Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1891–1898 (2014)
Tang, J., Jiang, N., Yu, W.: Gradient local binary pattern for convolutional neural networks. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 744–748. IEEE (2021)
Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wang, F., et al.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156–3164 (2017)
Wang, T., Zhu, J.Y., Torralba, A., Efros, A.A.: Dataset distillation. arXiv preprint arXiv:1811.10959 (2018)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Yang, J., Martinez, B., Bulat, A., Tzimiropoulos, G.: Knowledge distillation via adaptive instance normalization. arXiv preprint arXiv:2003.04289 (2020)
Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4133–4141 (2017)
Zagoruyko, S., Komodakis, N.: Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)
Zhang, L., Chen, X., Tu, X., Wan, P., Xu, N., Ma, K.: Wavelet knowledge distillation: towards efficient image-to-image translation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12464–12474 (2022)
Acknowledgement
This research is supported by Sichuan Science and Technology Program (No. 2022YFG0324), SWUST Doctoral Research Foundation under Grant 19zx7102.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Huang, X. et al. (2023). Optimizing Knowledge Distillation via Shallow Texture Knowledge Transfer. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1791. Springer, Singapore. https://doi.org/10.1007/978-981-99-1639-9_54
Download citation
DOI: https://doi.org/10.1007/978-981-99-1639-9_54
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1638-2
Online ISBN: 978-981-99-1639-9
eBook Packages: Computer ScienceComputer Science (R0)