Convolutional Residual Memory Networks

Abstract

Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers and the performance vs. depth trend is moving towards networks in excess of 1000 layers. In such extremely deep architectures the vanishing or exploding gradient problem becomes a key issue. Recent evidence also indicates that convolutional networks could benefit from an interface to explicitly constructed memory mechanisms interacting with a CNN feature processing hierarchy. Correspondingly, we propose and evaluate a memory mechanism enhanced convolutional neural network architecture based on augmenting convolutional residual networks with a long short term memory mechanism. We refer to this as a convolutional residual memory network. To the best of our knowledge this approach can yield state of the art performance on the CIFAR-100 benchmark and compares well with other state of the art techniques on the CIFAR-10 and SVHN benchmarks. This is achieved using networks with more breadth, much less depth and much less overall computation relative to comparable deep ResNets without the memory mechanism. Our experiments and analysis explore the importance of the memory mechanism, network depth, breadth, and predictive performance.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Striving for Simplicity: The All Convolutional Net
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Wide Residual Networks
• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• Fractional Max-Pooling
• Deep Networks with Stochastic Depth
• Identity Mappings in Deep Residual Networks
• All you need is a good init
• Delving Deeper into Convolutional Networks for Learning Video Representations
• Swapout: Learning an ensemble of deep architectures
• Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree

Cited by in corpus (5)

• Residual Networks of Residual Networks: Multilevel Residual Networks
• Recent Advances in Deep Learning: An Overview
• Deep Convolutional Neural Network Design Patterns
• Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation
• Batch-normalized Recurrent Highway Networks