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

Socpus ID

85055694038 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85055694038

This document is currently not available here.

Share

COinS