ImageNet pre-trained models with batch normalization
Computer Vision and Pattern Recognition
2016-12-07 v2
Abstract
Convolutional neural networks (CNN) pre-trained on ImageNet are the backbone of most state-of-the-art approaches. In this paper, we present a new set of pre-trained models with popular state-of-the-art architectures for the Caffe framework. The first release includes Residual Networks (ResNets) with generation script as well as the batch-normalization-variants of AlexNet and VGG19. All models outperform previous models with the same architecture. The models and training code are available at http://www.inf-cv.uni-jena.de/Research/CNN+Models.html and https://github.com/cvjena/cnn-models
Cite
@article{arxiv.1612.01452,
title = {ImageNet pre-trained models with batch normalization},
author = {Marcel Simon and Erik Rodner and Joachim Denzler},
journal= {arXiv preprint arXiv:1612.01452},
year = {2016}
}