Interleaved Structured Sparse Convolutional Neural Networks
Abstract
In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels. In addition to structured sparse kernels, low-rank kernels and the product of low-rank kernels, the product of structured sparse kernels, which is a framework for interpreting the recently-developed interleaved group convolutions (IGC) and its variants (e.g., Xception), has been attracting increasing interests. Motivated by the observation that the convolutions contained in a group convolution in IGC can be further decomposed in the same manner, we present a modularized building block, IGC-V2: Interleaved structured sparse convolutions. It generalizes interleaved group convolutions, which is composed of two structured sparse kernels, to the product of more structured sparse kernels, further eliminating the redundancy. We present the complementary condition and the balance condition to guide the design of structured sparse kernels, obtaining a balance among three aspects: Model size, computation complexity and classification accuracy. Experimental results demonstrate the advantage on the balance among these three aspects compared to interleaved group convolutions and Xception, and competitive performance compared to other state-of-the-art architecture design methods.
Publication Date
12-14-2018
Publication Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Number of Pages
8847-8856
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPR.2018.00922
Copyright Status
Unknown
Socpus ID
85055694038 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85055694038
STARS Citation
Xie, Guotian; Wang, Jingdong; Zhang, Ting; Lai, Jianhuang; and Hong, Richang, "Interleaved Structured Sparse Convolutional Neural Networks" (2018). Scopus Export 2015-2019. 10578.
https://stars.library.ucf.edu/scopus2015/10578