Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.16795363 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>MDCC v1.0 — First public code release</p> <p>This release publishes the codebase for our article "<strong>Feature mixing-driven dynamic contrastive consistency learning for robust source-free unsupervised domain adaptation</strong>", which is being submitted to <em>The Visual Computer</em>. We are opening the implementation to support reproducibility during editorial review and for the community.</p> <p><strong>What's included</strong></p> <ul> <li>Core MDCC implementation: Feature Mixing module, dynamic contrastive consistency learning, and a divide-and-conquer training schedule.</li> <li>Training scripts and example configs.</li> <li>Dataset preparation notes for Office-31, Office-Home, VisDA-C, and DomainNet-126.</li> </ul> <p><strong>Quick start</strong></p> <ul> <li>Prepare datasets and run training as described in the README.</li> </ul> <p><strong>Notes</strong></p> <ul> <li>Citation information will be added after submission/decision.</li> </ul>