Log In Sign Up

PolyNet: A Pursuit of Structural Diversity in Very Deep Networks

by   Xingcheng Zhang, et al.

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 that on multi-crops from 3.7


page 1

page 2

page 3

page 4


Power series expansion neural network

In this paper, we develop a new neural network family based on power ser...

Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions

The driving force behind deep networks is their ability to compactly rep...

Rethinking the Inception Architecture for Computer Vision

Convolutional networks are at the core of most state-of-the-art computer...

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Very deep convolutional networks have been central to the largest advanc...

Accelerated Training for Massive Classification via Dynamic Class Selection

Massive classification, a classification task defined over a vast number...

Code Repositories


The Github Repo for PolyNet

view repo