SOTAVerified

All you need is a good init

2015-11-19ICLR 2015Code Available1· sign in to hype

Dmytro Mishkin, Jiri Matas

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Layer-sequential unit-variance (LSUV) initialization - a simple method for weight initialization for deep net learning - is proposed. The method consists of the two steps. First, pre-initialize weights of each convolution or inner-product layer with orthonormal matrices. Second, proceed from the first to the final layer, normalizing the variance of the output of each layer to be equal to one. Experiment with different activation functions (maxout, ReLU-family, tanh) show that the proposed initialization leads to learning of very deep nets that (i) produces networks with test accuracy better or equal to standard methods and (ii) is at least as fast as the complex schemes proposed specifically for very deep nets such as FitNets (Romero et al. (2015)) and Highway (Srivastava et al. (2015)). Performance is evaluated on GoogLeNet, CaffeNet, FitNets and Residual nets and the state-of-the-art, or very close to it, is achieved on the MNIST, CIFAR-10/100 and ImageNet datasets.

Tasks

AllImage Classification

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
CIFAR-10Fitnet4-LSUVPercentage correct94.2—Unverified
CIFAR-100Fitnet4-LSUVPercentage correct72.3—Unverified
MNISTFitnet-LSUV-SVMPercentage error0.4—Unverified

Reproductions