Giter Site home page Giter Site logo

Comments (3)

Hzzone avatar Hzzone commented on September 26, 2024 1

You are right, you should get the final clustering results via spherical kmeans on the target encoder's features.

from propos.

Hzzone avatar Hzzone commented on September 26, 2024

The features after projection head from the target encoder (ema-updated one).

from propos.

4fee8fea avatar 4fee8fea commented on September 26, 2024

Thanks for answering, please excuse my interruption.

Should I get the final clustering results via spherical kmeans on the target encoder's features, OR other ways instead?

P.S. The conclusion below is impressive:

directly using the representations learned by BYOL for k-means clustering outperforms previous work including the contrastive-based ones.

from propos.

Related Issues (16)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.