Jiaolong / Self Supervised Da
Licence: mit
self-supervised domain adaptation
Stars: ✭ 36
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Self Supervised Da
lidar transfer
Code for Langer et al. "Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks", IROS, 2020.
Stars: ✭ 54 (+50%)
Mutual labels: domain-adaptation
Mmt
[ICLR-2020] Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification.
Stars: ✭ 345 (+858.33%)
Mutual labels: domain-adaptation
Transfer Learning Library
Transfer-Learning-Library
Stars: ✭ 678 (+1783.33%)
Mutual labels: domain-adaptation
robustness
Robustness and adaptation of ImageNet scale models. Pre-Release, stay tuned for updates.
Stars: ✭ 63 (+75%)
Mutual labels: domain-adaptation
Pytorch Adda
A PyTorch implementation for Adversarial Discriminative Domain Adaptation
Stars: ✭ 329 (+813.89%)
Mutual labels: domain-adaptation
Eanet
EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Stars: ✭ 380 (+955.56%)
Mutual labels: domain-adaptation
Meta-SelfLearning
Meta Self-learning for Multi-Source Domain Adaptation： A Benchmark
Stars: ✭ 157 (+336.11%)
Mutual labels: domain-adaptation
Domainadaptation
Repository for the article "Unsupervised domain adaptation for medical imaging segmentation with self-ensembling".
Stars: ✭ 27 (-25%)
Mutual labels: domain-adaptation
Deep Transfer Learning
A collection of implementations of deep domain adaptation algorithms
Stars: ✭ 331 (+819.44%)
Mutual labels: domain-adaptation
Adaptsegnet
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
Stars: ✭ 654 (+1716.67%)
Mutual labels: domain-adaptation
Salad
A toolbox for domain adaptation and semi-supervised learning. Contributions welcome.
Stars: ✭ 257 (+613.89%)
Mutual labels: domain-adaptation
Cross Domain Detection
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [Inoue+, CVPR2018].
Stars: ✭ 320 (+788.89%)
Mutual labels: domain-adaptation
Dann
pytorch implementation of Domain-Adversarial Training of Neural Networks
Stars: ✭ 400 (+1011.11%)
Mutual labels: domain-adaptation
SHOT-plus
code for our TPAMI 2021 paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"
Stars: ✭ 46 (+27.78%)
Mutual labels: domain-adaptation
Multitask Learning
Awesome Multitask Learning Resources
Stars: ✭ 361 (+902.78%)
Mutual labels: domain-adaptation
Generalizing Reid
Repository of the paper "Generalizing Person Re-Identification by Camera-Aware Instance Learning and Cross-Domain Mixup"
Stars: ✭ 28 (-22.22%)
Mutual labels: 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 (+23458.33%)
Mutual labels: domain-adaptation
Tf Dann
Domain-Adversarial Neural Network in Tensorflow
Stars: ✭ 556 (+1444.44%)
Mutual labels: domain-adaptation
Self-supervised Domain Adaptation
Repository for the paper "Self-supervised Domain adaptation for Computer Vision Tasks".
@article{self-supervised-da:2019,
title={Self-supervised Domain Adaptation for Computer Vision Tasks},
author={Jiaolong, Xu and Liang, Xiao and Antonio M. López},
journal={IEEE Access},
volume={7},
pages={156694-156706}
year={2019}
}
Requirements
-
python3.5+
-
pytorch 1.0+
Prepare dataset
Please find the PACS dataset from this link
The directories of the dataset are as following:
.
├── datasets
│ └── PACS
│ └── kfold
│ ├── art_painting
│ ├── cartoon
│ ├── photo
│ └── sketch
Running experiments
The configuration files for each experiment can be found at config/ folder.
For example:
python3 main.py --config configs/rotate_pacs_photo.yaml
To reproduce the results, running each experiment for three repeatitions with random seeds from 100, 200 and 300.
Results
| Method | art paint. | cartoon | sketches | photo | Avg. |
|---|---|---|---|---|---|
| SRC[1] | 77.85 | 74.86 | 67.74 | 95.73 | 79.05 |
| JigGen[1] | 84.88 | 81.07 | 79.05 | 97.96 | 85.74 |
| Ours(SRC) | 79.33 | 76.75 | 64.40 | 96.39 | 79.22 |
| Ours(Jigsaw) | 84.93 | 83.85 | 69.04 | 93.92 | 82.94 |
| Ours(Rot) | 89.35 | 84.14 | 74.49 | 98.24 | 86.56 |
Acknowledgement
Thanks for the open source of JigGen for reference implementation!
References
[1] F. M. Carlucci, A. D’Innocente, S. Bucci, B. Caputo, and T. Tommasi. Domain generalization by solving jigsaw puzzles. In CVPR, 2019.
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].