PyTorch implementation of "Seed, Expand, Constrain: Three Principles for Weakly-Supervised Image Segmentation", ECCV2016

This is not the official repository for this paper. For the official, please see the following links.

• Paper : https://arxiv.org/abs/1603.06098

• Official code : caffe implmentation

This is a work that proposes a new composite loss function for training convolutional neural network for the task of weakly-supervised semantic segmentation. Three novel loss functions are introduced:

• Seeding loss
• Expasion loss
• Contrain-to-boundary loss

19 Jul, 2020: upload PascalVOC pretrained model

02 Jan, 2020: upload COCO implementation

11 Nov, 2019: Initial upload

• Python 3.6
• PyTorch >= 1.0.0
• Torchvision >= 0.2.2
• PIL
• opencv-python (OpenCV for Python)
• tqdm
• tensorboardX

apt-get install libeigen3-dev

# this should be done after download the source..
pip install CRF/

Pascal VOC 2012 dataset (VOC2012) is used for this implementation.

• Download VOC2012 from here
• You can see the detail of VOC2012 in http://host.robots.ox.ac.uk/pascal/VOC/voc2012/index.html

We use ImageNet pretrained model which is coverted from Caffe.

• Download the pretrained model from here
• You can convert it on your own. Please see here for more details.

• download the source code & localization cue preparation

git clone https://github.com/halbielee/SEC_pytorch.git
cd SEC_pytorch 

# localizatio-cue preparation
gzip -kd datalist/PascalVOC/localization_cues.pickle.gz

• train

# Before executing this, please set the appropriate dataset path
bash script/train.sh

• test (generate the prediction map)

# Before executing this, please set the appropriate dataset path and other options..
bash script/test_multiprocess.sh

• evaluation (calculate the performance)

# Before executing this, please set the appropriate prediction_map / gt_map path
bash script/evaluation.sh

We evaluate the PyTorch implementation with hyperparms which the author provided without any other tuning.

Origin : Prediction : Ground Truth

{: widths="100%")