theo2021/OnDA
Source code for "Online Unsupervised Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions", ECCV 2022. This is the code has been implemented to perform training and evaluation of UDA approaches in continuous scenarios. The library has been implemented in PyTorch 1.7.1. Some newer versions should work as well.
This project helps machine learning engineers working on semantic segmentation tasks to improve model performance when deployment environments change. It takes a pre-trained semantic segmentation model and new, unlabeled image data from an evolving environment (like a camera moving between sunny and rainy conditions), and continuously adapts the model. The output is a more robust segmentation model that maintains accuracy over time without needing human re-labeling of new data.
No commits in the last 6 months.
Use this if you need to maintain high accuracy for semantic segmentation models in real-world applications where visual conditions or domains are constantly shifting, such as in autonomous driving or robotics.
Not ideal if your segmentation task involves static environments with consistent visual data, or if you are not working with deep learning models in PyTorch.
Stars
28
Forks
1
Language
Python
License
GPL-2.0
Category
Last pushed
Jun 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/theo2021/OnDA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
adapt-python/adapt
Awesome Domain Adaptation Python Toolbox
corenel/pytorch-adda
A PyTorch implementation for Adversarial Discriminative Domain Adaptation
jindongwang/transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers,...
thuml/Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
KaiyangZhou/Dassl.pytorch
A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.