修剪在CNN 模組當中冗餘的濾波器已受到越來越多關注。在本文中，我們提出了一種自適應二元收尋策略基於混合金字塔與分群(ABSHPC)的過濾器修剪方法。在我們的方法中，對於每個捲積層會先建造出一個混
合型金字塔結構來儲存每個濾波器的結構訊息。給定一個能容忍的精確度損失值(例如0.5%)，我們從最後一層捲積層開始到第一層，每層相對於前一層而言具有相等或較少的剪枝率，我們基於ABSHPC 的過程將所
有濾波器做最佳化的分群，每個群集均由混和金字塔中的中位數濾波器來表示，從而最大程度地去除冗餘的濾波器。基於CIFAR-10 數據集搭配VGG-16 和AlexNet，以較高精確度，透徹的實驗結果證明相對於最新方法，本文所提出的濾波器剪枝方法具有顯著的參數和浮點數運算減少的優點。

Pruning redundant filters in CNN models has received growing attention. In this thesis, we propose an adaptive binary search-first hybrid pyramidand clustering-based (ABSHPC-based) filter pruning method. In our method, for each convolutional layer, initially a hybrid pyramid data structure is constructed to store the hierarchical information of each filter. Given a tolerant accuracy loss, e.g. 0.5%, we begin from the last convolutional layer to the first layer; for each layer with less or equal pruning rate relative to its previous layer, our ABSHPC-based process is applied to optimally partition all filters to clusters, where each cluster is thus represented by the filter with the median root mean of the hybrid pyramid, leading to maximal removal of redundant filters. Based on the CIFAR-10 dataset and the VGG-16 and AlexNet models, with higher accuracy, the thorough experimental
results demonstrated the significant parameters and floating-point operations reduction merits of the proposed filter pruning method relative to the state-of-the-art methods.

[1] B. O. Ayinde and J. M. Zurada, “Building efficient convnets using redundant feature pruning,”arXiv preprint arXiv:1802.07653, 2018.
[2] V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A deep convolutional encoder-decoder architecture for image segmentation,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 12, pp. 2481-2495, Dec. 2017.
[3] P. J. Burt and E. H. Adelson, “The Laplacian pyramid as a compact image code,”IEEE Transactions on Communications, vol. 31, no. 4, pp. 532-540, Apr. 1983.
[4] H. Cai, L. Zhu, and S. Han, “ProxylessNAS: Direct neural architecture search on target task and hardware,” arXiv preprint arXiv:1812.00332, 2018.
[5] B. Chandra and R. K. Sharma, “Fast learning in deep neural networks,” Neurocomputing, vol. 171, pp. 1205–1215, Jan. 2016.
[6] C. F. Chen, G. G. Lee, V. Sritapan, and C. Y. Lin, “Deep convolutional neural network on iOS mobile devices,” IEEE International Workshop on Signal Processing Systems, pp. 130–135, Oct. 2016.
[7] S. Chen and Q. Zhao, “Shallowing Deep Networks: Layer-wise Pruning based on Feature Representations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 12, pp. 3048-3056, Dec. 2019.
[8] Y. Cheng, D. Wang, P. Zhou, and T. Zhang, “A survey of model compression and acceleration for deep neural networks,”arXiv preprint arXiv:1710.09282, 2017.
[9] T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein, Introduction to Algorithms (Asymptotic Notation), 3rd ed. London, U.K.: MIT Press, sec. 3.1, 2009.
[10] J. Deng, D. Wei, R. Socher, L. J. Li, K. Li, and F. F. Li, “ImageNet: a large-scale hierarchical image database,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255, 2009.
[11] M. Denil, B. Shakibi, L. Dinh, M. Ranzato, and N. de Freitas, “Predicting parameters in deep learning,” International Conference on Neural Information Processing Systems, pp. 2148–2156, 2013.
[12] Execution code. Accessed: 26 Jan. 2019. [Online]. Available: ftp://140.118.175.164/Model_Compression/Codes.
[13] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In Advances in Neural Information Processing Systems, pp. 2672–2680, 2014.
[14] S. Han, H. Mao, and W. J. Dally, “Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,” Proceedings of the International Conference on Learning Representations, no. 6, pp. 1-14,2016.
[15] S. Han, J. Pool, J. Tran, and W. J. Dally, “Learning both weights and connections for efficient neural network,” Advances in neural information processing systems, pp. 1135-1143, 2015.
[16] K. He, G. Gkioxari, P. Dollar, and R. Girshick, “Mask r-cnn,” IEEE International Conference on Computer Vision, pp. 2980–2988, 2017.
[17] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” arXiv preprint arXiv:1512.03385, 2015.
[18] Y. He, G. Kang, X. Dong, Y. Fu, and Y. Yang, “Soft filter pruning for accelerating deep convolutional neural networks,”International Joint Conferences on Artificial Intelligence, pp. 2234–2240, 2018.
[19] Y. He, J. Lin, Z. Liu, H. Wang, L. J. Li, and S. Han, “Amc: Automl for model compression and acceleration on mobile devices,” European Conference on Computer Vision, pp. 784-800, 2018.
[20] Y. He, P. Liu, Z. Wang, Z. Hu, and Y. Yang, “Filter pruning via geometric median for deep convolutional neural networks acceleration,”IEEE Conference on Computer Vision and Pattern Recognition, pp. 4340-4349, 2019.
[21] Y. He, X. Zhang, and J. Sun, “Channel pruning for accelerating very deep neural networks,”IEEE International Conference on Computer Vision, pp. 1398-1402, 2017.
[22] G. E. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” NIPS Deep Learning and Representation Learning Workshop, pp. 1-9, 2015.
[23] M. Jaderberg, A. Vedaldi, and A. Zisserman, “Speeding up convolutional neural networks with low rank expansions,” arXiv preprint arXiv:1405.3866, 2014.
[24] A. Krizhevsky, I. Sutskever, and G. Hinton, “ImageNet classification with deep convolutional neural networks,” Conference on Neural Information Processing Systems, pp. 1097–1105, 2012.
[25] Y. Lecun, L. Bottou, Y. Bengio, P. Haffner “Optimal brain damage,” Proceedings of the IEEE, pp. 2278-2324, Vol.86, No.11, Nov. 1998.
[26] C. H. Lee and L. H. Chen, “A fast search algorithm for vector quantization using mean pyramid of codewords,” IEEE Transactions on Comminucations, vol. 43, no. 2/3/4, pp. 1697-1702, Feb. 1995.
[27] H. Li, A. Kadav, I. Durdanovic, H. Samet, and H. P. Graf, “Pruning filters for efficient convnets,” International Conference on Learning Representations, pp. 1-13, 2017.
[28] S. Lin, R. Ji, Y. Li, C. Deng, and X. Li, “Toward compact convnets via structure-sparsity regularized filter prunin,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 2, pp. 574-588, Feb. 2020.
[29] S. J. Lin, K. L. Chung, and L. C. Chang, “An improved search algorithm for vector quantization using mean pyramid structure,” Pattern Recognition Letters, vol. 22, no. 3-4, pp. 373-379, Mar. 2001.
[30] C. T. Liu, T. W. Lin, Y. H. Wu, Y. S. Lin, H. Lee, Y. Tsao, and S. Y. Chien, “Computation-performance optimization of convolutional neural networks with redundant filter removal,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 66, no. 5, pp. 1908-1921, May 2019.
[31] C. T. Liu, Y. H. Wu, Y. S. Lin, and S. Y. Chien, “Computation-performance optimization of convolutional neural networks with redundant kernel removal,” International Symposium on Circuits and Systems, pp. 1–5, May 2018.
[32] Z. Liu, J. Li, Z. Shen, G. Huang, S. Yan, and C. Zhang, “Learning efficient convolutional networks through network slimming,”IEEE International Conference on Computer Vision, pp. 2755–2763, 2017.
[33] Z. Liu, M. Sun, T. Zhou, G. Huang, and T. Darrell, “Rethinking the value of network pruning,”arXiv preprint arXiv:1810.05270, 2018.
[34] J. H. Luo, J. Wu, and W. Lin, “Thinet: A filter level pruning method for deep neural network compression,” arXiv preprint arXiv:1707.06342, 2017.
[35] J. H. Luo, H. Zhang, H. Y. Zhou, C. W. Xie, J. Wu, and W. Lin, “ThiNet: pruning CNN filters for a thinner net,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 10, pp. 2525-2538, Oct. 2019.
[36] O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” International Conference On Medical Image Computing & Computer Assisted Intervention, pp. 234–241, 2015.
[37] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
[38] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” arXiv preprint arXiv:1409.4842, 2014.
[39] VGG-16 Architecture https://www.cs.toronto.edu/~frossard/post/vgg16/
[40] K. Wang, Z. Liu, Y. Lin, J. Lin, and S. Han, “Haq: Hardware-aware automated quantization with mixed precision,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 8612-8620, 2019.
[41] W. Yang, L. Jin, S. Wang, Z. Cu, X. Chen, and L. Chen, “Thinning of convolutional neural network with mixed pruning,” IET Image Processing, vol. 13, no. 5, pp. 779-784, May 2019.
[42] X. Zhang, J. Zou, K. He, and J. Sun, “Accelerating very deep convolutional networks for classification and detection,” IEEE Transactions