MDPM: A MATLAB repository from yanweifu

MDPM: Mid-level Deep Pattern Mining

Introduction

This is the source code package of the algorithm described in the paper Mid-level Deep Pattern Mining which has been accepted by CVPR 2015. More details are provided on the project page. This package has been tested using Matlab 2014a on a 64-bit Linux machine. This code is for research purposes only.

Citing MDPM

If you find MDPM useful in your research, please consider citing:

@inproceedings{LiLSH15CVPR,
    author = {Yao Li and Lingqiao Liu and Chunhua Shen and Anton van den Hengel},
    title = {Mid-level Deep Pattern Mining},
    booktitle = {Computer Vision and Pattern Recognition},
    year = {2015}
}

Installing MDPM

Prerequisites
Caffe: install Caffe by following its installation instructions. Do not forget to run make matcaffe to compile Caffe's Matlab interface. You also need to download Caffe's reference model (run download_model_binary.py models/bvlc_reference_caffenet from scripts) and the ImageNet mean file (run get_ilsvrc_aux.sh from data/ilsvrc12 ). Note: As we only use Caffe CNN as a feature extractor, installing Caffe using the CPU mode is OK.
Apriori algorithm: we use this implementation. Click the link to download this package. You need to uncompress it and run make to compile it in the apriori/apriori/src. Detailed usage of this package can be found here.
Liblinear: download liblinear and compile it by following its instructions.
KSVDS-Box v11: as we use the im2colstep function in this toolbox, you need to download and compile it (im2colstep is found in ksvdsbox11/private).
Configuring MDPM
Download MDPM: git clone https://github.com/yaoliUoA/MDPM.
Download MIT Indoor dataset from here.
Open init.m in the Matlab. Change values of sereval variables based on your configuration, including conf.pathToLiblinear, conf.pathToCaffe, conf.dataset and conf.imgDir based on your local configuration.
Copy the executable file aprior under directory apriori/apriori/src and paste it under mining directory.
Copy the mex file im2colstep and paste it under cnn directory.
Runing MDPM
Run the demo.m. It should be working properly if you have followed aforementioned instructions.
Important: It may takes some time to get the final classification result, so it is suggested to run MDPM on a cluster where jobs can be run in parallel. The *.sh scripts are provided to submit jobs on a cluster.

Pre-computed models

For MIT Indoor dataset, we have provided some pre-computed models 0. Pre-trained element detectors. After uncompressing the downloaded file, copy the .mat files to data/MIT67/detCom_lda_128_32_150 directory (create it by yourself), you should be able to run the feaEncodingMultiscaleSPM_lda.m from encoding to generate image features if cnn features have already been extracted.
0. Pre-computed image features. After uncompressing the downloaded file, copy the .mat files to data/MIT67/feaFinal_128_32_150 directory (create it by yourself), you should be able to run classify.m from classify directly to reproduce the classification result in the paper.

Feedback

If you have any issues (question, feedback) or find bugs in the code, please contact yao.li01@adelaide.edu.au.

yanweifu/MDPM