Check the preview of 2nd version of this platform being developed by the open MLCommons taskforce on automation and reproducibility as a free, open-source and technology-agnostic on-prem platform.

All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation

lib:6d14f1d963c61415 (v1.0.0)

Authors: Di Xie,Jiang Xiong,Shiliang Pu
Where published: CVPR 2017 7
ArXiv: 1703.01827
Document:  PDF  DOI 
Abstract URL: http://arxiv.org/abs/1703.01827v3


Deep neural network is difficult to train and this predicament becomes worse as the depth increases. The essence of this problem exists in the magnitude of backpropagated errors that will result in gradient vanishing or exploding phenomenon. We show that a variant of regularizer which utilizes orthonormality among different filter banks can alleviate this problem. Moreover, we design a backward error modulation mechanism based on the quasi-isometry assumption between two consecutive parametric layers. Equipped with these two ingredients, we propose several novel optimization solutions that can be utilized for training a specific-structured (repetitively triple modules of Conv-BNReLU) extremely deep convolutional neural network (CNN) WITHOUT any shortcuts/ identity mappings from scratch. Experiments show that our proposed solutions can achieve distinct improvements for a 44-layer and a 110-layer plain networks on both the CIFAR-10 and ImageNet datasets. Moreover, we can successfully train plain CNNs to match the performance of the residual counterparts. Besides, we propose new principles for designing network structure from the insights evoked by orthonormality. Combined with residual structure, we achieve comparative performance on the ImageNet dataset.

Relevant initiatives  

Related knowledge about this paper Reproduced results (crowd-benchmarking and competitions) Artifact and reproducibility checklists Common formats for research projects and shared artifacts Reproducibility initiatives

Comments  

Please log in to add your comments!
If you notice any inapropriate content that should not be here, please report us as soon as possible and we will try to remove it within 48 hours!