Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks.

作者: Vincent Gripon , Yoshua Bengio , Matthieu Arzel , Nicolas Farrugia , Ghouthi Boukli Hacene

DOI:

关键词:

摘要: Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity strongly limits their usability budget-constrained devices embedded devices. In this paper, we propose combination new pruning technique quantization scheme that effectively reduce memory usage convolutional layers CNNs, replace complex operation by low-cost multiplexer. We perform experiments on CIFAR10, CIFAR100 SVHN show proposed method achieves almost accuracy, while drastically reducing footprints. also an efficient hardware architecture accelerate CNN operations. The is pipeline accommodates multiple working at same time speed up inference process.

参考文章(24)
Karen Simonyan, Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition computer vision and pattern recognition. ,(2014)
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791
Benjamin Graham, Fractional Max-Pooling arXiv: Computer Vision and Pattern Recognition. ,(2014)
Sungjoo Yoo, Taelim Choi, Lu Yang, Dongjun Shin, Eunhyeok Park, Yong-Deok Kim, Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications arXiv: Computer Vision and Pattern Recognition. ,(2015)
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition computer vision and pattern recognition. pp. 770- 778 ,(2016) , 10.1109/CVPR.2016.90
Yoshua Bengio, Matthieu Courbariaux, Roland Memisevic, Zhouhan Lin, Neural Networks with Few Multiplications arXiv: Learning. ,(2015)
Forrest N. Iandola, William J. Dally, Khalid Ashraf, Song Han, Matthew W. Moskewicz, Kurt Keutzer, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size arXiv: Computer Vision and Pattern Recognition. ,(2016)
Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi, XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks Computer Vision – ECCV 2016. pp. 525- 542 ,(2016) , 10.1007/978-3-319-46493-0_32
Yoshua Bengio, Matthieu Courbariaux, Ran El-Yaniv, Itay Hubara, Daniel Soudry, Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 arXiv: Learning. ,(2016)
Nikos Komodakis, Sergey Zagoruyko, Wide Residual Networks arXiv: Computer Vision and Pattern Recognition. ,(2016)