jxhuang0508 / hcl Goto Github PK
View Code? Open in Web Editor NEW<Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data> in NIPS 2021
License: MIT License
<Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data> in NIPS 2021
License: MIT License
Hello, could you please release the source-only and the final pretrained models on SYNTHIA datasets?
Hello, about cityscapes ->foggy cityscapes, what is the foggy level in your evaluation? Is it similar to the evaluation method in SFOD (i.e. foggy level=ALL). As far as I know, the evaluation level of some articles is 0.02
Hello, could you please release the code for image classification?
Thanks a lot!
Hi, thank you very much for opensourcing such a wonderful code!
Can you provide the code for classification tasks, i.e., office31, officehome and VisDA.
Thanks in advance!
I feel like the implementation applies ADVENT as a additional content while training in target domain, which was not mentioned in the paper? Can you provide more details about the implementation? Thank you :)
For HCID loss, the paper mentions "r indicates the reliability of each key...use the classification entropy to estimate the reliability of
each key". How is this reliability estimated in detail? Is there any formula?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.