Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/cvi-szu/ccam

[CVPR 2022] C2AM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation

https://github.com/cvi-szu/ccam

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.2%) to scientific vocabulary

Keywords

contrastive-learning image-segmentation weakly-supervised-learning weakly-supervised-segmentation
Last synced: 5 months ago · JSON representation

Repository

[CVPR 2022] C2AM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation

Basic Info
  • Host: GitHub
  • Owner: CVI-SZU
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 5.05 MB
Statistics
  • Stars: 193
  • Watchers: 4
  • Forks: 26
  • Open Issues: 13
  • Releases: 0
Topics
contrastive-learning image-segmentation weakly-supervised-learning weakly-supervised-segmentation
Created almost 4 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License

README.md

C2AM (Unsupervised)

Update (2022-12-12)

We update the evaluation results using ResNet50 as both localization and classfication backbone. Table is also updated in our Arxiv paper.

| Method | Loc Back. | Cls Back. | CUB (top1/top5 loc) | CUB (GT-Known) | ImageNet (top1/top5 loc) | ImageNet (GT-Known) | |:---------:|:-----------:|:----:|:----:|:----:|:----:|:----:| | ORNet | VGG16 | VGG16 | 67.74 / 80.77 | 86.20 | 52.05 / 63.94 | 68.27 | | PSOL | ResNet50 | ResNet50 | 70.68 / 86.64 | 90.00 | 53.98 / 63.08 | 65.44 | | C2AM (supervised initialization) | ResNet50 | ResNet50 | 76.36 / 89.15 | 93.40 | 54.41 / 64.77 | 67.80 | | C2AM (unsupervised initialization) | ResNet50 | ResNet50 | 74.76 / 87.37 | 91.54 | 54.65 / 65.05 | 68.07 |

Code repository for our paper "C2AM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation" in CVPR 2022.

:heart_eyes: Code for our paper "CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation" in CVPR 2022 is also available here.

The repository includes full training, evaluation, and visualization codes on CUB-200-2011, ILSVRC2012, and PASCAL VOC2012 datasets.

We provide the extracted class-agnostic bounding boxes (on CUB-200-2011 and ILSVRC2012) and background cues (on PASCAL VOC12) from here.

Dependencies

  • Python 3
  • PyTorch 1.7.1
  • OpenCV-Python
  • Numpy
  • Scipy
  • MatplotLib
  • Yaml
  • Easydict

Dataset

CUB-200-2011

You will need to download the images (JPEG format) in CUB-200-2011 dataset from here. Make sure your data/CUB_200_2011 folder is structured as follows:

├── CUB_200_2011/ | ├── images | ├── images.txt | ├── bounding_boxes.txt | ... | └── train_test_split.txt

You will need to download the images (JPEG format) in ILSVRC2012 dataset from here. Make sure your data/ILSVRC2012 folder is structured as follows:

ILSVRC2012

├── ILSVRC2012/ | ├── train | ├── val | ├── val_boxes | | ├——val | | | ├—— ILSVRC2012_val_00050000.xml | | | ├—— ... | ├── train.txt | └── val.txt

PASCAL VOC2012

You will need to download the images (JPEG format) in PASCAL VOC2012 dataset from here. Make sure your data/VOC2012 folder is structured as follows:

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

For WSOL task

please refer to the directory of './WSOL'

cd WSOL

For WSSS task

please refer to the directory of './WSSS'

cd WSSS

Comparison with CAM

CUSTOM DATASET

As CCAM is an unsupervised method, it can be applied to various scenarios, like ReID, Saliency detection, or skin lesion detection. We provide an example to apply CCAM on your custom dataset like 'Market-1501'.

cd CUSTOM

Reference

If you are using our code, please consider citing our paper.

@InProceedings{Xie_2022_CVPR, author = {Xie, Jinheng and Xiang, Jianfeng and Chen, Junliang and Hou, Xianxu and Zhao, Xiaodong and Shen, Linlin}, title = {C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {989-998} } @article{xie2022contrastive, title={Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation}, author={Xie, Jinheng and Xiang, Jianfeng and Chen, Junliang and Hou, Xianxu and Zhao, Xiaodong and Shen, Linlin}, journal={arXiv preprint arXiv:2203.13505}, year={2022} }

Owner

  • Name: Computer Vision Institute, SZU
  • Login: CVI-SZU
  • Kind: organization
  • Location: Shenzhen Univeristy, Shenzhen, China

Computer Vision Institute, Shenzhen University

GitHub Events

Total
  • Issues event: 1
  • Watch event: 6
  • Fork event: 2
Last Year
  • Issues event: 1
  • Watch event: 6
  • Fork event: 2

Issues and Pull Requests

Last synced: 11 months ago

All Time
  • Total issues: 28
  • Total pull requests: 0
  • Average time to close issues: about 2 months
  • Average time to close pull requests: N/A
  • Total issue authors: 20
  • Total pull request authors: 0
  • Average comments per issue: 4.29
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 3.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • YH-2023 (3)
  • tungts1101 (2)
  • rjy-fighting (2)
  • roseyunzi (2)
  • a6177738 (1)
  • Aoran0215 (1)
  • lucasdavid (1)
  • jokingww (1)
  • Sierkinhane (1)
  • TomorrowJW (1)
  • NathanZhang1104 (1)
  • YingLv1106 (1)
  • YYDS-cc (1)
  • xiaoyaod (1)
  • MsterDC (1)
Pull Request Authors
Top Labels
Issue Labels
bug (1) enhancement (1) help wanted (1)
Pull Request Labels