IGCV$2$: Interleaved Structured Sparse Convolutional Neural Networks

TL;DR

This paper introduces IGCV$2$, a modular neural network building block that uses interleaved structured sparse convolutions to reduce redundancy, improve efficiency, and maintain high accuracy in convolutional neural networks.

Contribution

It generalizes interleaved group convolutions to a product of multiple structured sparse kernels, optimizing the trade-off among model size, computation, and accuracy.

Findings

Demonstrates improved balance among size, complexity, and accuracy.

Achieves competitive performance with state-of-the-art architectures.

Outperforms interleaved group convolutions and Xception in experiments.

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, {IGCV$2$:} 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.