{"id":13637740,"url":"https://github.com/Luffy03/CISC-R","last_synced_at":"2025-04-19T12:32:15.448Z","repository":{"id":179581722,"uuid":"574796892","full_name":"Luffy03/CISC-R","owner":"Luffy03","description":"[TPAMI 2022] Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation","archived":false,"fork":false,"pushed_at":"2023-07-08T01:58:28.000Z","size":3936,"stargazers_count":51,"open_issues_count":0,"forks_count":9,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-08-03T01:11:48.941Z","etag":null,"topics":["semantic-segmentation","semi-supervised-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Luffy03.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2022-12-06T04:54:59.000Z","updated_at":"2024-07-15T10:43:33.000Z","dependencies_parsed_at":"2024-01-14T08:54:40.633Z","dependency_job_id":"e3fa9a84-5dce-417a-8bb9-7d094a5c442b","html_url":"https://github.com/Luffy03/CISC-R","commit_stats":null,"previous_names":["luffy03/cisc-r"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Luffy03%2FCISC-R","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Luffy03%2FCISC-R/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Luffy03%2FCISC-R/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Luffy03%2FCISC-R/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Luffy03","download_url":"https://codeload.github.com/Luffy03/CISC-R/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223799375,"owners_count":17204772,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["semantic-segmentation","semi-supervised-learning"],"created_at":"2024-08-02T01:00:28.141Z","updated_at":"2024-11-09T07:31:15.690Z","avatar_url":"https://github.com/Luffy03.png","language":"Python","funding_links":[],"categories":["2023"],"sub_categories":[],"readme":"# CISC-R\nCode for TPAMI 2022 paper, [**\"Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation\"**](https://ieeexplore.ieee.org/document/10005033).\n\nAuthors: Linshan Wu, \u003ca href=\"https://scholar.google.com/citations?hl=en\u0026user=Gfa4nasAAAAJ\"\u003eLeyuan Fang\u003c/a\u003e, \u003ca href=\"https://scholar.google.com/citations?hl=zh-CN\u0026user=bHSKDuYAAAAJ\"\u003eXingxin He\u003c/a\u003e, Min He, \u003ca href=\"https://scholar.google.com/citations?hl=zh-CN\u0026user=73trMQkAAAAJ\"\u003eJiayi Ma\u003c/a\u003e, and \u003ca href=\"https://scholar.google.com/citations?user=nZizkQ0AAAAJ\u0026hl\"\u003eZhun Zhong\u003c/a\u003e\n\n## Abstract\nSemi-supervised semantic segmentation aims to learn a semantic segmentation model via limited labeled images and\nadequate unlabeled images. The key to this task is generating reliable pseudo labels for unlabeled images. Existing methods mainly\nfocus on producing reliable pseudo labels based on the confidence scores of unlabeled images while largely ignoring the use of\nlabeled images with accurate annotations. In this paper, we propose a Cross-Image Semantic Consistency guided Rectifying (CISC-R)\napproach for semi-supervised semantic segmentation, which explicitly leverages the labeled images to rectify the generated pseudo\nlabels. Our CISC-R is inspired by the fact that images belonging to the same class have a high pixel-level correspondence. Specifically,\ngiven an unlabeled image and its initial pseudo labels, we first query a guiding labeled image that shares the same semantic\ninformation with the unlabeled image. Then, we estimate the pixel-level similarity between the unlabeled image and the queried labeled\nimage to form a CISC map, which guides us to achieve a reliable pixel-level rectification for the pseudo labels.\n\n## Getting Started\n### Prepare Dataset\n- Pascal: [JPEGImages](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar) | [SegmentationClass](https://drive.google.com/file/d/1ikrDlsai5QSf2GiSUR3f8PZUzyTubcuF/view?usp=sharing)\n- Cityscapes: [leftImg8bit](https://www.cityscapes-dataset.com/file-handling/?packageID=3) | [gtFine](https://drive.google.com/file/d/1E_27g9tuHm6baBqcA7jct_jqcGA89QPm/view?usp=sharing)\n- COCO: [train2017](http://images.cocodataset.org/zips/train2017.zip) | [val2017](http://images.cocodataset.org/zips/val2017.zip) | [masks](https://drive.google.com/file/d/166xLerzEEIbU7Mt1UGut-3-VN41FMUb1/view?usp=sharing)\n```\n├── [Your Pascal Path]\n    ├── JPEGImages\n    └── SegmentationClass\n    \n├── [Your Cityscapes Path]\n    ├── leftImg8bit\n    └── gtFine\n    \n├── [Your COCO Path]\n    ├── train2017\n    ├── val2017\n    └── masks\n```\n### Pretrained Backbone:\n[ResNet-50](https://download.pytorch.org/models/resnet50-0676ba61.pth) | [ResNet-101](https://download.pytorch.org/models/resnet101-63fe2227.pth) | [Xception-65](https://drive.google.com/open?id=1_j_mE07tiV24xXOJw4XDze0-a0NAhNVi)\n```\n├── ./pretrained\n    ├── resnet50.pth\n    ├── resnet101.pth\n    └── xception.pth\n```\n### Train and Eval\n```bash \npython train.py\npython eval.py\n```\n\n## Acknowledgement\nWe thank [ST++](https://github.com/LiheYoung/ST-PlusPlus) for part of their codes, processed datasets, data partitions, and pretrained models.\n\n## Citation ✏️ 📄\nIf you find this repo useful for your research, please consider citing the paper as follows:\n```\n@ARTICLE{CISC_R2022,\n  author={Wu, Linshan and Fang, Leyuan and He, Xingxin and He, Min and Ma, Jiayi and Zhong, Zhun},\n  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, \n  title={Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation}, \n  year={2023},\n  volume={45},\n  number={7},\n  pages={8827-8844},\n  doi={10.1109/TPAMI.2022.3233584}}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLuffy03%2FCISC-R","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FLuffy03%2FCISC-R","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLuffy03%2FCISC-R/lists"}