zhengzangw/DoPrompt

Official implementation of PCS in essay "Prompt Vision Transformer for Domain Generalization"

33
/ 100
Emerging

This project offers a method to train computer vision models that perform well across different visual environments or datasets, even if they haven't seen data from all those environments during training. It takes in various image datasets from different "domains" (like different lighting conditions or art styles) and produces a robust image classification model. This is for machine learning researchers and practitioners who build and deploy computer vision systems.

No commits in the last 6 months.

Use this if you need to develop an image classification model that maintains high accuracy when applied to new, unseen visual environments or data distributions.

Not ideal if you are looking for a pre-trained, ready-to-use model or a solution for tasks other than image classification, or if you don't work with deep learning frameworks like PyTorch.

computer-vision machine-learning-research domain-adaptation image-recognition model-robustness
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

50

Forks

4

Language

Python

License

MIT

Last pushed

Jan 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/zhengzangw/DoPrompt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.