Abstract
Knowledge distillation (KD) is an effective and widely used technique of model compression which enables the deployment of deep networks in low-memory or fast-execution scenarios. Feature-based knowledge distillation is an important component of KD which leverages intermediate layers to supervise the training procedure of a student network. Nevertheless, the potential mismatch of intermediate layers may be counterproductive in the training procedure. In this paper, we propose a novel distillation framework, termed Decoupled Spatial Pyramid Pooling Knowledge Distillation, to distinguish the importance of regions in feature maps. Specifically, we reveal that (1) spatial pyramid pooling is an outstanding method to define the knowledge and (2) the lower activation regions in feature maps play a more important role in KD. Our experiments on CIFAR-100 and Tiny-ImageNet achieve state-of-the-art results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Hints mean the output of a teacher’s hidden layers that supervise the student’s training.
References
Ahn, S., Hu, S.X., Damianou, A.C., Lawrence, N.D., Dai, Z.: Variational information distillation for knowledge transfer. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 9163–9171 (2019). https://doi.org/10.1109/CVPR.2019.00938
Anil, R., Pereyra, G., Passos, A., Ormándi, R., Dahl, G.E., Hinton, G.E.: Large scale distributed neural network training through online distillation. In: 6th International Conference on Learning Representations, ICLR (2018)
Ba, J., Caruana, R.: Do deep nets really need to be deep? In: Advances in Neural Information Processing Systems, pp. 2654–2662 (2014)
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013). https://doi.org/10.1109/TPAMI.2013.50
Buciluundefined, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 535–541, New York, NY, USA (2006). https://doi.org/10.1145/1150402.1150464
Chen, D., Mei, J., Wang, C., Feng, Y., Chen, C.: Online knowledge distillation with diverse peers. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI, pp. 3430–3437 (2020)
Chen, D., et al.: Cross-layer distillation with semantic calibration. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI, pp. 7028–7036 (2021)
Chen, G., Choi, W., Yu, X., Han, T.X., Chandraker, M.: Learning efficient object detection models with knowledge distillation. In: Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, pp. 742–751 (2017)
Cheng, X., Rao, Z., Chen, Y., Zhang, Q.: Explaining knowledge distillation by quantifying the knowledge. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12925–12935 (2020)
Courbariaux, M., Bengio, Y., David, J.: Binaryconnect: training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems, pp. 3123–3131 (2015)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171–4186 (2019). https://doi.org/10.18653/v1/N19-1423
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)
Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vision 129(6), 1789–1819 (2021). https://doi.org/10.1007/s11263-021-01453-z
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. In: 4th International Conference on Learning Representations, ICLR (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346–361. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_23
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
Heo, B., Lee, M., Yun, S., Choi, J.Y.: Knowledge transfer via distillation of activation boundaries formed by hidden neurons. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI, pp. 3779–3787 (2019). https://doi.org/10.1609/aaai.v33i01.33013779
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Comput. Sci. 14(7), 38–39 (2015)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Huang, Z., Wang, N.: Like what you like: knowledge distill via neuron selectivity transfer. arXiv preprint arXiv:1707.01219 (2017)
Jin, X., et al.: Knowledge distillation via route constrained optimization. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV, pp. 1345–1354 (2019). https://doi.org/10.1109/ICCV.2019.00143
Kim, J., Park, S., Kwak, N.: Paraphrasing complex network: Network compression via factor transfer. In: Bengio, S., Wallach, H.M., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, pp. 2765–2774 (2018)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Handbook of Systemic Autoimmune Diseases 1(4), 7 (2009)
Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: 5th International Conference on Learning Representations, ICLR (2017)
Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_8
Mirzadeh, S., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI, pp. 5191–5198 (2020)
Müller, R., Kornblith, S., Hinton, G.E.: When does label smoothing help? In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems. pp. 4696–4705 (2019)
Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 3967–3976 (2019). https://doi.org/10.1109/CVPR.2019.00409
Passalis, N., Tefas, A.: Learning deep representations with probabilistic knowledge transfer. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 283–299. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_17
Peng, B., Jin, X., Li, D., Zhou, S., Wu, Y., Liu, J., Zhang, Z., Liu, Y.: Correlation congruence for knowledge distillation. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV, pp. 5006–5015 (2019). https://doi.org/10.1109/ICCV.2019.00511
Pereyra, G., Tucker, G., Chorowski, J., Kaiser, L., Hinton, G.E.: Regularizing neural networks by penalizing confident output distributions. In: 5th International Conference on Learning Representations, ICLR (2017)
Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-net: Imagenet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525–542. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_32
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: 3rd International Conference on Learning Representations, ICLR (2015)
Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. pp. 4510–4520 (2018). https://doi.org/10.1109/CVPR.2018.00474
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, ICLR (2015)
Song, J., Chen, Y., Ye, J., Song, M.: Spot-adaptive knowledge distillation. IEEE Trans. Image Process. 31, 3359–3370 (2022)
Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. In: 8th International Conference on Learning Representations, ICLR (2020)
Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV, pp. 1365–1374 (2019). https://doi.org/10.1109/ICCV.2019.00145
Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 7130–7138 (2017). https://doi.org/10.1109/CVPR.2017.754
Yuan, L., Tay, F.E.H., Li, G., Wang, T., Feng, J.: Revisiting knowledge distillation via label smoothing regularization. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 3902–3910 (2020). https://doi.org/10.1109/CVPR42600.2020.00396
Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: 5th International Conference on Learning Representations, ICLR (2017)
Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 6848–6856 (2018). https://doi.org/10.1109/CVPR.2018.00716
Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 4320–4328 (2018). https://doi.org/10.1109/CVPR.2018.00454
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 Switzerland AG
About this paper
Cite this paper
Gao, L., Gao, H. (2023). Feature Decoupled Knowledge Distillation via Spatial Pyramid Pooling. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13846. Springer, Cham. https://doi.org/10.1007/978-3-031-26351-4_44
Download citation
DOI: https://doi.org/10.1007/978-3-031-26351-4_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26350-7
Online ISBN: 978-3-031-26351-4
eBook Packages: Computer ScienceComputer Science (R0)