Coder Social home page Coder Social logo

wildphoton / randconv Goto Github PK

View Code? Open in Web Editor NEW
58.0 58.0 6.0 32 KB

Code for ICLR2021 paper "Robust and Generalizable Visual Representation Learning via Random Convolutions"

Shell 1.10% Python 98.90%
data-augmentation deep-learning domain-generalization texture-bias

randconv's People

Contributors

wildphoton avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

randconv's Issues

Missing Synth. Dataset

Hello!
When trying to run the script, I found that the “synth” dataset doesn't seem to download automatically. And the link provided in the code comments is not working for me either. I had to run the code without this dataset for now, hope you can provide other ways to download the dataset.

Deep-All results on PACS

Hi, Thanks for the interesting work.

You said in your paper that your Deep-All results on PACS are not directly comparable with Jigen due to different implementations. Could you please clarify what are the differences between your implementation and JiGen? You know your Deep-All result is almost 5% (on Avg.) lower than that of Carlucci's implementations. In addition, do you know what causes this difference? augmentation, model initialization, optimizer, learning rate decay strategy, or something else?

Thanks a lot.

About the consistency loss

Hi, thanks for sharing your code. For the function F.kl_div(), the first parameter is input and the second is target. I am confused why the target is not p_mixture on L401-L403?
Thanks.

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.