ImageNet pre-trained models with batch normalization

TL;DR

This paper introduces new ImageNet pre-trained CNN models, including ResNets, AlexNet, and VGG19 variants, which outperform previous models of the same architecture and are available for the community.

Contribution

The paper provides a new set of pre-trained models with batch normalization for popular architectures, improving performance and offering resources for the research community.

Findings

Models outperform previous versions of the same architecture

Includes ResNets, AlexNet, and VGG19 variants with batch normalization

Models and code are publicly available

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