Did you considered using Dino-V3 instead of Dino-V2, as the initialization backbone?

Open
#157 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
20/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Quiet
Domain
computer-vision, machine-learning

Research direction

The issue does not name any files, tests, or entry points. First determine how MoGe initializes its backbone and whether DINO-V3 is supported in the existing experiments; done would require a decided implementation or experiment scope and a way to validate the resulting model.

Written by the indexing model from the issue text.

Description

Hello authors,

Thanks so much for your amazing open source work!

With the release of Moge-3, I was wondering, did you consider using Dino-V3 as the initialization backbone, instead of Dino-V2, in your experiments?

Thanks again!
Prakhar

Dominant language
JavaScript
Stars
3k
Forks
234
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from microsoft/MoGe

All issues in microsoft/MoGe

Similar issues

More JavaScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.