Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add an example of implementation Federated Learning to ReID #58

Open
weimingwill opened this issue Apr 23, 2021 · 7 comments
Open

Add an example of implementation Federated Learning to ReID #58

weimingwill opened this issue Apr 23, 2021 · 7 comments

Comments

@weimingwill
Copy link

Propose to add a new example of implementation of federated learning to ReID. It is more close to real-world applications.

The details can refer to the paper in ACM MM'20: Performance Optimization of Federated Person Re-identification via Benchmark Analysis

The original implementation can be found at https://github.com/cap-ntu/FedReID.

@ugvddm
Copy link

ugvddm commented Apr 23, 2021

Sounds like a good idea. would you like introduce it in community reguler meeting next week?
Thanks.

@weimingwill
Copy link
Author

Sure. Maybe the next regular meeting after this week's one.

@ugvddm
Copy link

ugvddm commented Apr 26, 2021

nice

@ugvddm
Copy link

ugvddm commented May 10, 2021

We are designing reID based on the edge-cloud collaborative AI framework sedna. A community contributor did research :https://docs.qq.com/pdf/DSEdKd0F0TWd2blpl.
Your work as you said above, I think we can work together to build a amazing reID feature.

@weimingwill
Copy link
Author

Looks cool. This doc focuses more on person ReID inference. While using federated learning focuses more on training.

@ugvddm
Copy link

ugvddm commented May 11, 2021

Agree with you, FedReID can improve re-identification accuracy in our current work, Do you have time for the regular meeting this Thursday? Please introduce your work to community, and discuss how to collaborate.

@weimingwill
Copy link
Author

Sure.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants