Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Luffy03/CISC-R
[TPAMI 2022] Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation
https://github.com/Luffy03/CISC-R
semantic-segmentation semi-supervised-learning
Last synced: about 1 month ago
JSON representation
[TPAMI 2022] Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation
- Host: GitHub
- URL: https://github.com/Luffy03/CISC-R
- Owner: Luffy03
- Created: 2022-12-06T04:54:59.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-07-08T01:58:28.000Z (over 1 year ago)
- Last Synced: 2024-08-03T01:11:48.941Z (5 months ago)
- Topics: semantic-segmentation, semi-supervised-learning
- Language: Python
- Homepage:
- Size: 3.75 MB
- Stars: 51
- Watchers: 3
- Forks: 9
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- Awesome-Semi-Supervised-Semantic-Segmentation - Code - R)|[Paper](https://ieeexplore.ieee.org/document/10005033)| (2023)
README
# CISC-R
Code for TPAMI 2022 paper, [**"Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation"**](https://ieeexplore.ieee.org/document/10005033).
Authors: Linshan Wu, Leyuan Fang, Xingxin He, Min He, Jiayi Ma, and Zhun Zhong
## Abstract
Semi-supervised semantic segmentation aims to learn a semantic segmentation model via limited labeled images and
adequate unlabeled images. The key to this task is generating reliable pseudo labels for unlabeled images. Existing methods mainly
focus on producing reliable pseudo labels based on the confidence scores of unlabeled images while largely ignoring the use of
labeled images with accurate annotations. In this paper, we propose a Cross-Image Semantic Consistency guided Rectifying (CISC-R)
approach for semi-supervised semantic segmentation, which explicitly leverages the labeled images to rectify the generated pseudo
labels. Our CISC-R is inspired by the fact that images belonging to the same class have a high pixel-level correspondence. Specifically,
given an unlabeled image and its initial pseudo labels, we first query a guiding labeled image that shares the same semantic
information with the unlabeled image. Then, we estimate the pixel-level similarity between the unlabeled image and the queried labeled
image to form a CISC map, which guides us to achieve a reliable pixel-level rectification for the pseudo labels.
## Getting Started
### Prepare Dataset
- 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)
- Cityscapes: [leftImg8bit](https://www.cityscapes-dataset.com/file-handling/?packageID=3) | [gtFine](https://drive.google.com/file/d/1E_27g9tuHm6baBqcA7jct_jqcGA89QPm/view?usp=sharing)
- 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)
```
├── [Your Pascal Path]
├── JPEGImages
└── SegmentationClass
├── [Your Cityscapes Path]
├── leftImg8bit
└── gtFine
├── [Your COCO Path]
├── train2017
├── val2017
└── masks
```
### Pretrained Backbone:
[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)
```
├── ./pretrained
├── resnet50.pth
├── resnet101.pth
└── xception.pth
```
### Train and Eval
```bash
python train.py
python eval.py
```
## Acknowledgement
We thank [ST++](https://github.com/LiheYoung/ST-PlusPlus) for part of their codes, processed datasets, data partitions, and pretrained models.
## Citation ✏️ 📄
If you find this repo useful for your research, please consider citing the paper as follows:
```
@ARTICLE{CISC_R2022,
author={Wu, Linshan and Fang, Leyuan and He, Xingxin and He, Min and Ma, Jiayi and Zhong, Zhun},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation},
year={2023},
volume={45},
number={7},
pages={8827-8844},
doi={10.1109/TPAMI.2022.3233584}}
```