ImageNet pre-trained models with batch normalization

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

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Microsoft COCO Captions: Data Collection and Evaluation Server
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• VQA: Visual Question Answering
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Dynamic Memory Networks for Visual and Textual Question Answering
• Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
• Generation and Comprehension of Unambiguous Object Descriptions
• Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
• Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks
• Modeling Context in Referring Expressions
• Part Detector Discovery in Deep Convolutional Neural Networks
• Designing Deep Networks for Surface Normal Estimation

Cited by in corpus (16)

• A systematic study of the class imbalance problem in convolutional neural networks
• Ternary Neural Networks with Fine-Grained Quantization
• ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations
• Player Identification in Hockey Broadcast Videos
• Mixed Low-precision Deep Learning Inference using Dynamic Fixed Point
• WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic
• CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network
• Extreme 3D Face Reconstruction: Seeing Through Occlusions
• Improving the convergence of SGD through adaptive batch sizes
• Democratizing Artificial Intelligence in Healthcare: A Study of Model Development Across Two Institutions Incorporating Transfer Learning
• Towards Recognizing New Semantic Concepts in New Visual Domains
• A Survey on Green Deep Learning
• Self-supervised Data Bootstrapping for Deep Optical Character Recognition of Identity Documents
• Fixed-point Factorized Networks
• AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks
• Exploring Correlations in Multiple Facial Attributes through Graph Attention Network