Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[CVPR 2024] Official implement of <Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation>
| Date | Stars |
|---|---|
| 2026-07-31 | 411 |
| 2026-08-06 | 410 |
Today
-1 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# [CVPR 2024] Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation [zhixiang wei](https://zxwei.site)<sup>1</sup>, [lin chen](https://lin-chen.site)<sup>2</sup>, et al. <br /> <sup>1</sup> University of Science of Techonology of China <sup>2</sup> Shanghai AI Laboratory [](https://paperswithcode.com/sota/domain-adaptation-on-cityscapes-to-acdc?p=stronger-fewer-superior-harnessing-vision) <br /> [](https://paperswithcode.com/sota/domain-generalization-on-gta-to-avg?p=stronger-fewer-superior-harnessing-vision) <br /> [](https://paperswithcode.com/sota/domain-generalization-on-gta5-to-cityscapes?p=stronger-fewer-superior-harnessing-vision) <br /> Project page: https://zxwei.site/rein Paper: https://arxiv.org/pdf/2312.04265.pdf Rein is a efficient and robust fine-tuning method, specifically developed to effectively utilize **Vision Foundation Models (VFMs)** for **Domain Generalized Semantic Segmentation (DGSS)**. It achieves **SOTA on Cityscapes to ACDC, and GTAV to Cityscapes+Mapillary+BDD100K**. Using only synthetic data, Rein achieved an mIoU of **78.4\% on Cityscapes** validation set! Using only the data from the Cityscapes training set, we achieved an average mIoU of **77.6% on ACDC** test set!  ## Visualization Trained on Cityscapes, Rein generalizes to unseen driving scenes and cities: Nighttime Shanghai, Foggy Countryside, and Rainy Hollywood. [![night]](https://user-images.githubusercontent.com/54713447/330731120-f9e3fafd-ebb7-462d-bc9b-92b1bde96e23.mp4) [![rain]](https://user-images.githubusercontent.com/54713447/330731135-7c504893-6ead-41de-9820-b1e5ff267475.mp4) [![fog]](https://user-images.githubusercontent.com/54713447/330731083-9ab5c758-b2b6-4eac-bb63-9a546f2f89fe.mp4) ## 🔥 News! * 🔥 Welcome to check out our latest work: [Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models](https://www.arxiv.org/abs/2508.01667)! * 🔥 Delighted to announce that ours work [HQCLIP: Leveraging Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models](https://arxiv.org/abs/2507.22431) were accepted by ICCV 2025! * 🔥 We warmly congratulate **SoMA** (<https://ysj9909.github.io/SoRA.github.io/>) for receiving a **CVPR 2025 Highlight**! Built upon the **Rein** codebase, SoMA demonstrates **outstanding semantic segmentation performance** and has even successfully accomplished **object detection tasks**! * 🔥 To facilitate users in integrating reins into their own projects, we provide a simplified version of reins: [simple_reins](https://github.com/w1oves/Rein/tree/train/simple_reins). With this version, users can easily use reins as a feature extractor. (Note: This version has removed features related to mask2former) * We have uploaded the config for `ResNet` and `ConvNeXt`. * We have uploaded the checkpoint and config for `+1/16 of Cityscapes` training set, and it get **82.5% on the Cityscapes** validation set! * Rein is accepted in `CVPR2024`! * Using only the data from the Cityscapes training set, we achieved an average mIoU of **77.56% on the ACDC** test set! This result ranks **first** in the DGSS methods on the ACDC [benchmark](https://acdc.vision.ee.ethz.ch/submissions/65b6848187f1a5171cf44c34)! Checkpoint is avaliable at [release](https://github.com/w1oves/Rein/releases/tag/Cityscapes). * Using only synthetic data (UrbanSyn, GTAV, and Synthia), Rein achieved an mIoU
Excerpt of 16,491 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:98293868aeb1544d, desc:semantic segmentation