Timezone: »

 
Poster
CNNpack: Packing Convolutional Neural Networks in the Frequency Domain
Yunhe Wang · Chang Xu · Shan You · Dacheng Tao · Chao Xu

Mon Dec 05 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #159 #None
in Monday Posters »

Deep convolutional neural networks (CNNs) are successfully used in a number of applications. However, their storage and computational requirements have largely prevented their widespread use on mobile devices. Here we present an effective CNN compression approach in the frequency domain, which focuses not only on smaller weights but on all the weights and their underlying connections. By treating convolutional filters as images, we decompose their representations in the frequency domain as common parts (i.e., cluster centers) shared by other similar filters and their individual private parts (i.e., individual residuals). A large number of low-energy frequency coefficients in both parts can be discarded to produce high compression without significantly compromising accuracy. We relax the computational burden of convolution operations in CNNs by linearly combining the convolution responses of discrete cosine transform (DCT) bases. The compression and speed-up ratios of the proposed algorithm are thoroughly analyzed and evaluated on benchmark image datasets to demonstrate its superiority over state-of-the-art methods.

Keywords: Deep Learning or Neural Networks · Large Scale Learning and Big Data · (Other) Classification

Author Information

Yunhe Wang (Peking University)
Chang Xu (Peking University)
Shan You
Dacheng Tao (Nanyang Technological University)
Chao Xu (Peking University)

More from the Same Authors