Residual Networks of Residual Networks: Multilevel Residual Networks

Abstract

A residual-networks family with hundreds or even thousands of layers dominates major image recognition tasks, but building a network by simply stacking residual blocks inevitably limits its optimization ability. This paper proposes a novel residual-network architecture, Residual networks of Residual networks (RoR), to dig the optimization ability of residual networks. RoR substitutes optimizing residual mapping of residual mapping for optimizing original residual mapping. In particular, RoR adds level-wise shortcut connections upon original residual networks to promote the learning capability of residual networks. More importantly, RoR can be applied to various kinds of residual networks (ResNets, Pre-ResNets and WRN) and significantly boost their performance. Our experiments demonstrate the effectiveness and versatility of RoR, where it achieves the best performance in all residual-network-like structures. Our RoR-3-WRN58-4+SD models achieve new state-of-the-art results on CIFAR-10, CIFAR-100 and SVHN, with test errors 3.77%, 19.73% and 1.59%, respectively. RoR-3 models also achieve state-of-the-art results compared to ResNets on ImageNet data set.

IEEE Transactions on Circuits and Systems for Video Technology 2017

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Improving neural networks by preventing co-adaptation of feature detectors
• Striving for Simplicity: The All Convolutional Net
• FitNets: Hints for Thin Deep Nets
• Dark Forces in the Sky: Signals from Z' and the Dark Higgs
• Convolutional Residual Memory Networks

Cited by in corpus (11)

• Selective Kernel Networks
• On the Origin of Deep Learning
• Deep Convolutional Neural Network Design Patterns
• Age Group and Gender Estimation in the Wild with Deep RoR Architecture
• Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning
• Building a Regular Decision Boundary with Deep Networks
• Improving training of deep neural networks via Singular Value Bounding
• AFN: Attentional Feedback Network based 3D Terrain Super-Resolution
• MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
• Mixture separability loss in a deep convolutional network for image classification
• 4-Connected Shift Residual Networks