PolyNet: A Pursuit of Structural Diversity in Very Deep Networks

TL;DR

This paper introduces PolyInception modules to enhance deep network diversity, improving image recognition performance while managing computational costs, demonstrated by superior results on the ImageNet benchmark.

Contribution

The paper proposes PolyInception modules that increase structural diversity in deep networks, achieving better performance without significantly increasing computational costs.

Findings

PolyNet reduces top-5 error on ImageNet from 4.9% to 4.25%.

PolyNet outperforms Inception-ResNet-v2 on multi-crop validation.

Structural diversity via PolyInception improves deep network expressiveness.

Abstract

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 is met with a 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. The Very Deep PolyNet, designed following this direction, demonstrates substantial improvements over the state-of-the-art on the ILSVRC 2012 benchmark. Compared to Inception-ResNet-v2, it reduces the top-5 validation error on single crops from 4.9% to 4.25%, and that on multi-crops from 3.7% to 3.45%.