PolyNet: A Pursuit of Structural Diversity in Very Deep Networks

Xingcheng Zhang, Zhizhong Li, Chen Change Loy, Dahua Lin

Published 2016-11-17Version 1

A number of studies have shown that increasing the depth or width of convolutional networks is a rewarding approach to improve the performance of image recognition. In our study, however, we observed difficulties along both directions. On one hand, the pursuit for very deep networks are met with diminishing return and increased training difficulty; on the other hand, widening a network would result in a quadratic growth in both computational cost and memory demand. These difficulties motivate us to explore structural diversity in designing deep networks, a new dimension beyond just depth and width. Specifically, we present a new family of modules, namely the PolyInception, which can be flexibly inserted in isolation or in a composition as replacements of different parts of a network. Choosing PolyInception modules with the guidance of architectural efficiency can improve the expressive power while preserving comparable computational cost. A benchmark on the ILSVRC 2012 validation set demonstrates substantial improvements over the state-of-the-art. Compared to Inception-ResNet-v2, it reduces the top-5 error on single crops from 4.9% to 4.25%, and that on multi-crops from 3.7% to 3.45%.