[CVPR2024] Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation
- If you find this work helpful, don't hesitate to give us a ๐ !
Mar. 21st, 2024
: All Codes, logs, and checkpoints are available now๐ฅ๐ฅ๐ฅ- If you have any questions, please feel free to leave issues or contact us by [email protected].
We proposed a Separate and Conquer philosophy to effectively tackle the co-occurrence issue in WSSS.
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
The augmented annotations are from SBD dataset. The download link of the augmented annotations at
DropBox. After downloading SegmentationClassAug.zip
, you should unzip it and move it to VOCdevkit/VOC2012/
.
VOCdevkit/
โโโ VOC2012
โโโ Annotations
โโโ ImageSets
โโโ JPEGImages
โโโ SegmentationClass
โโโ SegmentationClassAug
โโโ SegmentationObject
wget http://images.cocodataset.org/zips/train2014.zip
wget http://images.cocodataset.org/zips/val2014.zip
To generate VOC style segmentation labels for COCO, you could use the scripts provided at this repo, or just download the generated masks from Google Drive.
COCO/
โโโ JPEGImages
โ โโโ train2014
โ โโโ val2014
โโโ SegmentationClass
โโโ train2014
โโโ val2014
Please refer to the requirements.txt.
We incorporate a regularization loss for segmentation. Please refer to the instruction for this python extension.
### train voc
bash run_train.sh scripts/train_voc.py [gpu_number] [master_port] [gpu_device] train_voc
### train coco
bash run_train.sh scripts/train_coco.py [gpu_numbers] [master_port] [gpu_devices] train_coco
### eval voc
bash run_evaluate_seg_voc.sh tools/infer_seg_voc.py [gpu_device] [checkpoint_path]
### eval coco
bash run_evaluate_seg_coco.sh tools/infer_seg_coco.py [gpu_number] [master_port] [gpu_device] [checkpoint_path]
Semantic performance on VOC and COCO. Logs and weights are available now.
Dataset | Backbone | Val | Test | Log | Weight |
---|---|---|---|---|---|
PASCAL VOC | ViT-B | 74.0 | 73.8 | log | weight |
MS COCO | ViT-B | 46.7 | - | log | weight |
Please cite our work if you find it helpful to your reseach. ๐
@article{yang2024separate,
title={Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation},
author={Yang, Zhiwei and Fu, Kexue and Duan, Minghong and Qu, Linhao and Wang, Shuo and Song, Zhijian},
journal={arXiv preprint arXiv:2402.18467},
year={2024}
}
This repo is built upon ToCo, DINO, and SupCon. Many thanks to their brilliant works!!!