Code for Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation [ECCV 2020 (oral)]
CVPR 2020 Learning from Imperfect Data (LID) workshop Best Paper Award and winner solution in WSSS Track of CVPR2020 LID challenge
===========================================================================
Authors: Guolei Sun, Wenguan Wang, Jifeng Dai, Luc Van Gool.
===========================================================================
-
Install Caffe: install prerequisites, then go to segmentation folder and run "make all -j4 && make pycaffe" to compile. To continue, make sure Caffe is installed correctly by referring to Caffe.
-
Download the PASCAL VOC 2012 and pretrained segmentation model. Put the segmentation model in folder segmentation/examples/seg/exp2/model/
-
Go to segmentation/examples/seg, change the dataset path when necessary, and run "python eval_res.py gpu_id exp2 model". You will get mIoU score of 66.2 on PASCAL VOC12 val set.
coattention classifer
If you find the code and dataset useful in your research, please consider citing:
@InProceedings{sun2020mining,
title={Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation},
author={Sun, Guolei and Wang, Wenguan and Dai, Jifeng and Van Gool, Luc},
booktitle={ECCV},
year={2020} }
This repository is based on OAA, thanks for their excellent work.
For questions, please contact sunguolei.kaust@gmail.com