lucasmansilla/DGvGS
Domain Generalization via Gradient Surgery
This project helps machine learning researchers improve the performance of image classification models when applied to new, unseen data environments. It takes existing image datasets (like PACS, VLCS, or Office-Home) and processes them to train models that are more robust. The output is a more generalized image classification model that performs better on new types of images.
No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner working on making image classification models generalize better across different visual domains without needing to retrain for each new domain.
Not ideal if you are looking for a plug-and-play solution for general image classification without a specific focus on domain generalization research.
Stars
51
Forks
7
Language
Python
License
MIT
Category
Last pushed
May 03, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lucasmansilla/DGvGS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
hectorLop/Conditional-Adversarial-Domain-Generalization-with-Single-Discriminator
Pytorch implementation of the paper: "Conditional Adversarial Domain Generalization With a...
PrasannaPulakurthi/SPM
Shuffle PatchMix (SPM) for Source-Free Domain Adaptation (ICIP 2025); patch-shuffle augmentation...
SakurajimaMaiii/TSD
[CVPR 2023] Feature Alignment and Uniformity for Test Time Adaptation
yasserben/DATUM
[CVPR-W 2023] Official Implementation of One-shot Unsupervised Domain Adaptation with...
mousecpn/DMC-Domain-Generalization-for-Underwater-Object-Detection
[Neurocomputing 2023] An official implementation of Achieving Domain Generalization in...