English

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

Keywords

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}
}
R2 v1 2026-06-22T17:13:47.559Z