Deep Co-occurrence Feature Learning for Visual Object Recognition

Ya-Fang Shih*, Yang-Ming Yeh*, Yen-Yu Lin, Ming-Fang Weng, Yi-Chang Lu, Yung-Yu Chuang
(CVPR 2017)

.
ā”œā”€ā”€ src/                  
ā”œā”€ā”€ data/                   
ā”‚   ā”œā”€ā”€ cub/          
ā”‚   ā””ā”€ā”€ models/         
ā”œā”€ā”€ exp/                   
ā”‚   ā”œā”€ā”€ cub-imdb.mat
ā”‚   ā”œā”€ā”€ deep_cooc_models/         
ā”‚   ā””ā”€ā”€ feature_maps/        
ā”œā”€ā”€ from-bcnn-package/                  
ā”œā”€ā”€ matconvnet/               
ā””ā”€ā”€ vlfeat/                 

Installation

  1. clone the Deep-COOC repository
  2. follow the intructions to install matconvnet
  3. download vlfeat toolbox, and put the files into vlfeat/
  4. download CUB-200-2011 dataset, and put the files into data/cub/
  5. download ImageNet-pretrained CNN models (in our experiments, we used the imagenet-resnet-152-dag model), and put them into data/models/
  6. run src/main.m

Deep Cooc

Deep Co-occurrence Feature Learning for Visual Object Recognition (CVPR 2017)

Deep Cooc Info

ā­ Stars 36
šŸ”— Homepage yafangshih.github.io
šŸ”— Source Code github.com
šŸ•’ Last Update 8 months ago
šŸ•’ Created 5 years ago
šŸž Open Issues 1
āž— Star-Issue Ratio 36
šŸ˜Ž Author yafangshih