Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior
Xiang Zhang, Nishant Vishwamitra, Hongxin Hu, Feng Luo
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In experiments, CrescendoNet with only 15 layers outperforms almost all networks without residual connections on benchmark datasets, CIFAR10, CIFAR100, and SVHN. Given sufficient amount of data as in SVHN dataset, CrescendoNet with 15 layers and 4.1M parameters can match the performance of DenseNet-BC with 250 layers and 15.3M parameters. CrescendoNet provides a new way to construct high performance deep convolutional neural networks without residual connections. Moreover, through investigating the behavior and performance of subnetworks in CrescendoNet, we note that the high performance of CrescendoNet may come from its implicit ensemble behavior, which differs from the FractalNet that is also a deep convolutional neural network without residual connections. Furthermore, the independence between paths in CrescendoNet allows us to introduce a new path-wise training procedure, which can reduce the memory needed for training.
TL;DR:We introduce CrescendoNet, a deep CNN architecture by stacking simple building blocks without residual connections.
Keywords:CNN, ensemble, image recognition
Enter your feedback below and we'll get back to you as soon as possible.