Modelpublic

tue-mps/videomt-dinov2-base-ytvis2019

sourceHugging Faceupdated 6mo agoView on Hugging Face

0likes7downloads

Model Card

VidEoMT-B on YouTube-VIS 2019

This repository contains the Hugging Face Transformers conversion of the official VidEoMT checkpoint yt_2019_vit_base_58.2.pth from tue-mps/VidEoMT.

Model details

—Architecture: VidEoMT with a DINOv2 ViT-B/14 with 4 register tokens backbone
—Task: video instance segmentation
—Dataset: YouTube-VIS 2019
—Input resolution: 640 x 640
—Number of frames: 2
—Paper: Your ViT is Secretly Also a Video Segmentation Model

Reported metrics

Metric	Value
AP	58.2
AR@10	66.5
FPS	251

The metrics above are the numbers reported by the authors in the official model zoo.

Usage

python

from transformers import AutoModelForUniversalSegmentation, AutoVideoProcessor

model_id = "tue-mps/videomt-dinov2-base-ytvis2019"
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.