RoyalVane / Clan
Licence: mit
( CVPR2019 Oral ) Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
Stars: ✭ 248
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Clan
adapt
Awesome Domain Adaptation Python Toolbox
Stars: ✭ 46 (-81.45%)
Mutual labels: transfer-learning, adversarial-learning, domain-adaptation
Awesome Domain Adaptation
A collection of AWESOME things about domian adaptation
Stars: ✭ 3,357 (+1253.63%)
Mutual labels: transfer-learning, domain-adaptation, adversarial-learning
Seg Uncertainty
IJCAI2020 & IJCV 2020 🌇 Unsupervised Scene Adaptation with Memory Regularization in vivo
Stars: ✭ 202 (-18.55%)
Mutual labels: semantic-segmentation, transfer-learning, domain-adaptation
Adaptsegnet
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
Stars: ✭ 654 (+163.71%)
Mutual labels: semantic-segmentation, domain-adaptation, adversarial-learning
Libtlda
Library of transfer learners and domain-adaptive classifiers.
Stars: ✭ 71 (-71.37%)
Mutual labels: transfer-learning, domain-adaptation
Deep Transfer Learning
Deep Transfer Learning Papers
Stars: ✭ 68 (-72.58%)
Mutual labels: transfer-learning, domain-adaptation
Seanet
Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation
Stars: ✭ 90 (-63.71%)
Mutual labels: semantic-segmentation, domain-adaptation
Awesome Transfer Learning
Best transfer learning and domain adaptation resources (papers, tutorials, datasets, etc.)
Stars: ✭ 1,349 (+443.95%)
Mutual labels: transfer-learning, domain-adaptation
Lsd Seg
Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
Stars: ✭ 99 (-60.08%)
Mutual labels: semantic-segmentation, domain-adaptation
Convolutional Handwriting Gan
ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (CVPR20)
Stars: ✭ 107 (-56.85%)
Mutual labels: transfer-learning, domain-adaptation
Segan
SegAN: Semantic Segmentation with Adversarial Learning
Stars: ✭ 143 (-42.34%)
Mutual labels: semantic-segmentation, adversarial-learning
Cross Domain ner
Cross-domain NER using cross-domain language modeling, code for ACL 2019 paper
Stars: ✭ 67 (-72.98%)
Mutual labels: transfer-learning, domain-adaptation
Gvb
Code of Gradually Vanishing Bridge for Adversarial Domain Adaptation (CVPR2020)
Stars: ✭ 52 (-79.03%)
Mutual labels: domain-adaptation, adversarial-learning
Ddc Transfer Learning
A simple implementation of Deep Domain Confusion: Maximizing for Domain Invariance
Stars: ✭ 83 (-66.53%)
Mutual labels: transfer-learning, domain-adaptation
Transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
Stars: ✭ 8,481 (+3319.76%)
Mutual labels: transfer-learning, domain-adaptation
Transfer Learning Library
Transfer-Learning-Library
Stars: ✭ 678 (+173.39%)
Mutual labels: transfer-learning, domain-adaptation
Shot
code released for our ICML 2020 paper "Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation"
Stars: ✭ 134 (-45.97%)
Mutual labels: transfer-learning, domain-adaptation
Cbst
Code for <Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training> in ECCV18
Stars: ✭ 146 (-41.13%)
Mutual labels: semantic-segmentation, domain-adaptation
Tf Dann
Domain-Adversarial Neural Network in Tensorflow
Stars: ✭ 556 (+124.19%)
Mutual labels: domain-adaptation, adversarial-learning
Dise Domain Invariant Structure Extraction
Pytorch Implementation -- All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation, CVPR 2019
Stars: ✭ 129 (-47.98%)
Mutual labels: semantic-segmentation, domain-adaptation
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation (CVPR2019)
This is a pytorch implementation of CLAN.
Oral Presentation Video
Prerequisites
- Python 3.6
- GPU Memory >= 11G
- Pytorch 1.0.0
Getting started
-
Download The GTA5 Dataset
-
Download The SYNTHIA Dataset
-
Download The Cityscapes Dataset
-
Download The imagenet pretraind model
The data folder is structured as follows:
├── data/
│ ├── Cityscapes/
| | ├── gtFine/
| | ├── leftImg8bit/
│ ├── GTA5/
| | ├── images/
| | ├── labels/
│ ├── SYNTHIA/
| | ├── RAND_CITYSCAPES/
│ └──
└── model/
│ ├── DeepLab_resnet_pretrained.pth
...
Train
CUDA_VISIBLE_DEVICES=0 python CLAN_train.py --snapshot-dir ./snapshots/GTA2Cityscapes
Evaluate
CUDA_VISIBLE_DEVICES=0 python CLAN_evaluate.py --restore-from ./snapshots/GTA2Cityscapes/GTA5_100000.pth --save ./result/GTA2Cityscapes_100000
Our pretrained model is available via Google Drive
Compute IoU
python CLAN_iou.py ./data/Cityscapes/gtFine/val result/GTA2Cityscapes_100000
Tip: The best-performance model might not be the final one in the last epoch. If you want to evaluate every saved models in bulk, please use CLAN_evaluate_bulk.py and CLAN_iou_bulk.py, the result will be saved in an Excel sheet.
CUDA_VISIBLE_DEVICES=0 python CLAN_evaluate_bulk.py
python CLAN_iou_bulk.py
Visualization Results
This code is heavily borrowed from the baseline AdaptSegNet
Citation
If you use this code in your research please consider citing
@article{luo2021category,
title={Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features},
author={Luo, Yawei and Liu, Ping and Zheng, Liang and Guan, Tao and Yu, Junqing and Yang, Yi},
journal={IEEE Transactions on Pattern Analysis \& Machine Intelligence (TPAMI)},
year={2021},
}
@inproceedings{luo2019Taking,
title={Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation},
author={Luo, Yawei and Zheng, Liang and Guan, Tao and Yu, Junqing and Yang, Yi},
booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2019}
}
Related works
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].