Deep Pyramidal Residual Networks with Separated Stochastic Depth

Abstract

On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy. In particular, ResNet and its improvements have broken the lowest error rate records. In this paper, we propose a method to successfully combine two ResNet improvements, ResDrop and PyramidNet. We confirmed that the proposed network outperformed the conventional methods; on CIFAR-100, the proposed network achieved an error rate of 16.18% in contrast to PiramidNet achieving that of 18.29% and ResNeXt 17.31%.

References in corpus (4)

• Densely Connected Convolutional Networks
• Aggregated Residual Transformations for Deep Neural Networks
• Deep Networks with Stochastic Depth
• Deep Pyramidal Residual Networks

Cited by in corpus (9)

• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Born Again Neural Networks
• A Survey on Neural Architecture Search
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• ShakeDrop Regularization for Deep Residual Learning
• Face Recognition: From Traditional to Deep Learning Methods
• VINNAS: Variational Inference-based Neural Network Architecture Search
• Learnable Image Encryption
• Learning Less-Overlapping Representations