[CVPR2024] Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation [](http://arxiv.org/abs/2402.18467)

News

• If you find this work helpful, don't hesitate to give us a :star2: !
• Mar. 21st, 2024: All Codes, logs, and checkpoints are available now🔥🔥🔥
• If you have any questions, please feel free to leave issues or contact us by zwyang21@m.fudan.edu.cn.

Overview

We proposed a Separate and Conquer philosophy to effectively tackle the co-occurrence issue in WSSS.

Data Preparation

PASCAL VOC 2012

1. Download

wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar

2. Segmentation Labels

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/
└── VOC2012
    ├── Annotations
    ├── ImageSets
    ├── JPEGImages
    ├── SegmentationClass
    ├── SegmentationClassAug
    └── SegmentationObject

MSCOCO 2014

1. Download

wget http://images.cocodataset.org/zips/train2014.zip
wget http://images.cocodataset.org/zips/val2014.zip

2. Segmentation Labels

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/
├── JPEGImages
│    ├── train2014
│    └── val2014
└── SegmentationClass
     ├── train2014
     └── val2014

Requirement

Please refer to the requirements.txt.

We incorporate a regularization loss for segmentation. Please refer to the instruction for this python extension.

Train SeCo

### 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

Evaluate SeCo

### 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]

Main Results

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

Citation

Please cite our work if you find it helpful to your reseach. :two_hearts:

@InProceedings{Yang_2024_CVPR,
    author    = {Yang, Zhiwei and Fu, Kexue and Duan, Minghong and Qu, Linhao and Wang, Shuo and Song, Zhijian},
    title     = {Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2024},
    pages     = {3606-3615}
}

Acknowledgement

This repo is built upon ToCo, DINO, and SupCon. Many thanks to their brilliant works!!!