Abstract
With the development of deep neural networks, compressing and accelerating deep neural networks without performance deterioration has become a research hotspot. Among all kinds of network compression methods, network pruning is one of the most effective and popular methods. Inspired by several property-based pruning methods and geometric topology, we focus the research of the pruning method on the extraction of feature map information. We predefine a metric, called TopologyHole, used to describe the feature map and associate it with the importance of the corresponding filter. In the exploration experiments, we find out that the average TopologyHole of the feature map for the same filter is relatively stable, regardless of the number of image batches the CNNs receive. This phenomenon proves TopologyHole is a data-independent metric and valid as a criterion for filter pruning. Through a large number of experiments, we have demonstrated that priorly pruning the filters with high-TopologyHole feature maps achieves competitive performance compared to the state-of-the-art. Notably, on ImageNet, TopologyHole reduces 45.0\(\%\) FLOPs by removing 40.9\(\%\) parameters on ResNet-50 with 75.71\(\%\), only a loss of 0.44\(\%\) in top-1 accuracy.
Similar content being viewed by others
References
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, pp. 91–99 (2015)
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)
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. In: Association for Computational Linguistics (2019)
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, vol. 1 (Long and Short Papers), pp. 4171–4186 (2019)
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)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: ICLR (2014)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241. Springer, Berlin (2015)
Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. Adv. Neural Inf. Process. Syst. 28, 1135–1143 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Denil, M., Shakibi, B., Dinh, L., Ranzato, M., De Freitas, N.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems, pp. 2148–2156 (2013)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In: ICLR (2016)
Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. In: Advances in Neural Information Processing Systems, pp. 2074–2082 (2016)
Chen, W., Wilson, J., Tyree, S., Weinberger, K., Chen, Y.: Compressing neural networks with the hashing trick. In: International Conference on Machine Learning, PMLR, pp. 2285–2294 (2015)
Chen, J., Liu, L., Liu, Y., Zeng, X.: A learning framework for n-bit quantized neural networks toward FPGAs. IEEE Trans. Neural Netw. Learn. Syst. 32(3), 1067–1081 (2020)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS (2014)
Z. Li, Y. Sun, G. Tian, L. Xie, Y. Liu, H. Su, Y. He, A compression pipeline for one-stage object detection model. J. Real Time Image Process. 18, 1949–1962 (2021)
Meng, B., Wang, L., He, Z., Jeon, G., Dou, Q., Yang, X.: Gradient information distillation network for real-time single-image super-resolution. J. Real Time Image Process. 18(2), 333–344 (2021)
Lebedev, V., Ganin, Y., Rakhuba, M., Oseledets, I., Lempitsky, V.: Speeding-up convolutional neural networks using fine-tuned CP-decomposition. In: ICLR (2015)
Denton, E., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in Neural Information Processing Systems, pp. 1269–1277 (2014)
Chang, C.H., Kehtarnavaz, N.: Computationally efficient image deblurring using low rank image approximation and its GPU implementation. J. Real Time Image Process. 12(3), 567–573 (2016)
Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint. arXiv:1704.04861
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(< 0.5\) mb model size (2016). arXiv preprint. arXiv:1602.07360
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convNets. In: ICLR, pp. 1–13 (2017)
He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1389–1397 (2017)
He, Y., Liu, P., Wang, Z., Hu, Z., Yang, Y.: Filter pruning via geometric median for deep convolutional neural networks acceleration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4340–4349 (2019)
Hu, H., Peng, R., Tai, Y.W., Tang, C.K.: Network trimming: a data-driven neuron pruning approach towards efficient deep architectures (2016). arXiv preprint. arXiv:1607.03250
Lin, M., Ji, R., Wang, Y., Zhang, Y., Zhang, B., Tian, Y., Shao, L.: Hrank: filter pruning using high-rank feature map. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1529–1538 (2020)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Huang, Z., Wang, N.: Data-driven sparse structure selection for deep neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 304–320 (2018)
Luo, J.H., Wu, J., Lin, W.: ThiNet: a filter level pruning method for deep neural network compression. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5058–5066 (2017)
Yu, R., Li, A., Chen, C.F., Lai, J.H., Morariu, V.I., Han, X., Gao, M., Lin, C.Y., Davis, L.S.: NISP: pruning networks using neuron importance score propagation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9194–9203 (2018)
Lin, S., Ji, R., Yan, C., Zhang, B., Cao, L., Ye, Q., Huang, F., Doermann, D.: Towards optimal structured CNN pruning via generative adversarial learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2790–2799 (2019)
Lin, M., Cao, L., Li, S., Ye, Q., Tian, Y., Liu, J., Tian, Q., Ji, R.: Filter sketch for network pruning. In: IEEE Transactions on Neural Networks and Learning Systems (2021)
Tian, G., Chen, J., Zeng, X., Liu, Y.: Pruning by training: a novel deep neural network compression framework for image processing. IEEE Signal Process. Lett. 28, 344–348 (2021)
Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11264–11272 (2019)
Lian, Y., Peng, P., Xu, W.: Filter pruning via separation of sparsity search and model training. Neurocomputing 462, 185–194 (2021)
Luo, J.H., Wu, J.: Autopruner: an end-to-end trainable filter pruning method for efficient deep model inference. Pattern Recognit. 107, 107461 (2020)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xu, X., Chen, J., Su, H. et al. Towards efficient filter pruning via topology. J Real-Time Image Proc 19, 639–649 (2022). https://doi.org/10.1007/s11554-022-01209-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-022-01209-z