Downloads · 30 days
9
9% of all-time downloads
videomt-dinov2-large-ytvis2022
tue-mps/videomt-dinov2-large-ytvis2022
videomt-dinov2-large-ytvis2022 is a image segmentation model from tue-mps. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for transformers.
This repository contains the Hugging Face Transformers conversion of the official VidEoMT checkpoint yt2022vitlarge42.6.pth from tue-mps/VidEoMT.
All-time downloads
96
Public
Parameters
318M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Image Segmentation
- Library
- transformers
- Model type
- videomt
- Access
- Public
- Created
- Mar 27, 2026
- Updated
- Mar 27, 2026
- SHA
- 0580c607
Model card
From the Hugging Face model README
VidEoMT-L on YouTube-VIS 2022
This repository contains the Hugging Face Transformers conversion of the official VidEoMT checkpoint
yt_2022_vit_large_42.6.pth from tue-mps/VidEoMT.
Model details
- Architecture: VidEoMT with a DINOv2 ViT-L/14 with 4 register tokens backbone
- Task: video instance segmentation
- Dataset: YouTube-VIS 2022
- Input resolution: 640 x 640
- Number of frames: 2
- Paper: Your ViT is Secretly Also a Video Segmentation Model
Reported metrics
| Metric | Value |
|---|---|
| AP^L | 42.6 |
| AR^L@10 | 48.1 |
| FPS | 161 |
The metrics above are the numbers reported by the authors in the official model zoo.
Usage
from transformers import AutoModelForUniversalSegmentation, AutoVideoProcessor
model_id = "tue-mps/videomt-dinov2-large-ytvis2022"
processor = AutoVideoProcessor.from_pretrained(model_id)
model = AutoModelForUniversalSegmentation.from_pretrained(model_id)
Use processor.post_process_instance_segmentation,
processor.post_process_panoptic_segmentation, or
processor.post_process_semantic_segmentation depending on the target task.
- Task
- Image Segmentation
- Library
- transformers
- Type
- videomt
- Created
- Mar 27, 2026
- Updated
- Mar 27, 2026