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%.

本研究提出了一种新型的深度网络架构——PolyInception，通过在网络不同区间柔性地插入PolyInception模块进行深度学习，并在架构效率指导下选择合适的模块，提高网络的表达能力，降低了计算成本，相较于同类网络，在ILSVRC 2012基准测试中，其top-5验证错误率分别从4.9%降至4.25%和从3.7%降至3.45%。

PolyNet：追求很深网络的结构多样性