ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network

Dongyoon HanSangdoo YunByeongho HeoYoungJoon Yoo

   Papers with code   Abstract  PDF

This paper addresses representational bottleneck in a network and propose a set of design principles that improves model performance significantly. We argue that a representational bottleneck may happen in a network designed by a conventional design and results in degrading the model performance... (read more)

Benchmarked Models