Home Projects logit-standardization-KD
logit-standardization-KD
Jupyter Notebook

logit-standardization-KD

[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation

by sunshangquan · GitHub
Stars
Forks
Created
Last commit
computer-visioncvcvprJupyter Notebook
View on GitHub
In plain words

Transfer knowledge from one AI model to another to improve performance using a method that adjusts their learning process.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
logit-standardization-KD — GitHub preview card
📈 Star history
386385
2026-07-202026-08-31
📈 Track logit-standardization-KD

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation

logit-standardization-KD has 385 stars on GitHub. It has been forked 31 times. logit-standardization-KD is written mainly in Jupyter Notebook. It has been in active development since 2024. Its main topics are computer-vision, cv, cvpr, cvpr2024.

Frequently asked questions

What is logit-standardization-KD?

[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation

Is logit-standardization-KD open source?

logit-standardization-KD is an open-source project.

Is logit-standardization-KD free?

Yes. logit-standardization-KD is free and open source — you can use, modify and self-host it.

What language is logit-standardization-KD written in?

logit-standardization-KD is written mainly in Jupyter Notebook.

🏅 Maintainer of this project?
olud.ai badge — logit-standardization-KD

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=sunshangquan-logit-standardization-kd)](https://olud.ai/project/sunshangquan-logit-standardization-kd.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.