Skip to content
Category-Aware Spatial Constraint for Weakly Supervised Detection
Python Shell C Cuda MATLAB C++
Branch: master
Clone or download

Latest commit

Fetching latest commit…
Cannot retrieve the latest commit at this time.

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
caffe-fast-rcnn @ 0dcd397
caffe-fwsl @ 5d18088
caffe-wsl @ 78b2f71
data
experiments
lib
models
tools
.gitignore
.gitmodules
LICENSE
README.md

README.md

CSC

Category-Aware Spatial Constraint for Weakly Supervised Detection

Citing CSC

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

@article{Shen_2019_TIP,
author = {Shen, Yunhang and Ji, Rongrong and Yang, Kuiyuan and Deng, Cheng and Wang, Changhu},
journal = {IEEE TRANSACTIONS ON IMAGE PROCESSING},
title = {{Category-Aware Spatial Constraint for Weakly Supervised Detection}},
year = {2019}
}

Contents

  1. Requirements: software
  2. Requirements: hardware
  3. Installation
  4. Usage

Requirements: software

  1. Requirements for Caffe and pycaffe (see: Caffe installation instructions)

Note: Caffe must be built with support for Python layers!

# In your Makefile.config, make sure to have this line uncommented
WITH_PYTHON_LAYER := 1
# Unrelatedly, it's also recommended that you use CUDNN
USE_CUDNN := 1
  1. Python packages you might not have: cython, python-opencv, easydict
  2. [Optional] MATLAB is required for official PASCAL VOC evaluation only. The code now includes unofficial Python evaluation code.

Requirements: hardware

  1. For training smaller networks (VGG_CNN_F, VGG_CNN_M_1024), a GPU with about 6G of memory suffices.
  2. For training lager networks (VGG16), you'll need a GPU with about 8G of memory.

Installation

  1. Clone the CSC repository
# Make sure to clone with --recursive
git clone --recursive https://github.com/shenyunhang/CSC.git
  1. We'll call the directory that you cloned CSC into CSC_ROOT

    Ignore notes 1 and 2 if you followed step 1 above.

    Note 1: If you didn't clone CSC with the --recursive flag, then you'll need to manually clone the caffe-wsl submodule:

    git submodule update --init --recursive

    Note 2: The caffe-wsl submodule needs to be on the wsl branch (or equivalent detached state). This will happen automatically if you followed step 1 instructions.

  2. Build the Cython modules

    cd $CSC_ROOT/lib
    make
  3. Build Caffe and pycaffe

    cd $CSC_ROOT/caffe-wsl
    # Now follow the Caffe installation instructions here:
    #   http://caffe.berkeleyvision.org/installation.html
    
    # If you're experienced with Caffe and have all of the requirements installed
    # and your Makefile.config in place, then simply do:
    make -j8 && make pycaffe
  4. Download the training, validation, test data and VOCdevkit

    wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
    wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
    wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar
  5. Extract all of these tars into one directory named VOCdevkit

    tar xvf VOCtrainval_06-Nov-2007.tar
    tar xvf VOCtest_06-Nov-2007.tar
    tar xvf VOCdevkit_08-Jun-2007.tar
  6. It should have this basic structure

    $VOCdevkit/                           # development kit
    $VOCdevkit/VOCcode/                   # VOC utility code
    $VOCdevkit/VOC2007                    # image sets, annotations, etc.
    # ... and several other directories ...
  7. Create symlinks for the PASCAL VOC dataset

    cd $CSC_ROOT/data
    ln -s $VOCdevkit VOCdevkit2007

    Using symlinks is a good idea because you will likely want to share the same PASCAL dataset installation between multiple projects.

  8. [Optional] follow similar steps to get PASCAL VOC 2010 and 2012

  9. [Optional] If you want to use COCO, please see some notes under data/README.md

  10. Follow the next sections to download pre-trained ImageNet models

Download object proposals

  1. Selective Search: original matlab code, python wrapper
  2. EdgeBoxes: matlab code
  3. MCG: matlab code

Download pre-trained ImageNet models

Pre-trained ImageNet models can be downloaded for the three networks described in the paper: ZF and VGG16.

cd $CSC_ROOT
./data/scripts/fetch_imagenet_models.sh

Usage

To train and test a CSC detector, use experiments/scripts/csc.sh. Output is written underneath $CSC_ROOT/output.

cd $CSC_ROOT
./experiments/scripts/csc.sh [GPU_ID] [NET] [--set ...]
# GPU_ID is the GPU you want to train on
# NET in {VGG_CNN_F, VGG_CNN_M_1024, VGG16} is the network arch to use
# --set ... allows you to specify configure options, e.g.
#   --set EXP_DIR seed_rng1701 RNG_SEED 1701

Example:

./experiments/scripts/csc.sh 0 VGG16 pascal_voc --set EXP_DIR csc

This will reproduction the VGG16 result in paper.

Trained CSC networks are saved under:

output/<experiment directory>/<dataset name>/

Test outputs are saved under:

output/<experiment directory>/<dataset name>/<network snapshot name>/

Other method

WSDDN:

./experiments/scripts/wsddn.sh 0 VGG16 pascal_voc --set EXP_DIR wsddn

or

./experiments/scripts/wsddn_x.sh 0 VGG16 pascal_voc --set EXP_DIR wsddn_x

ContextLocNet:

./experiments/scripts/contextlocnet.sh 0 VGG16 pascal_voc --set EXP_DIR contextlocnet

or

./experiments/scripts/contextlocnet_x.sh 0 VGG16 pascal_voc --set EXP_DIR contextlocnet_x
You can’t perform that action at this time.