Task
Image Segmentation
C
tue-mps/coco_panoptic_eomt_large_640
Image Segmentation·tue-mps· 38.1K· 13
EoMT (Encoder-only Mask Transformer) is a Vision Transformer (ViT) architecture designed for high-quality and efficient image segmentation. It was introduced in the CVPR 2025 highlight paper: Your ViT is Secretly an Image Segmentation Model by Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans, Narges Norouzi, Giuseppe Averta, Bastian Leibe, Gijs Dubbelman, and Daan de Geus.
# pull & run locally
pip install mlforge-sdk && mlforge pull tue-mps/coco_panoptic_eomt_large_640
pip install mlforge-sdk && mlforge pull tue-mps/coco_panoptic_eomt_large_640
Model details
Provider
tue-mps
Framework
transformers
Parameters
316.7M
Size
3.5 GB
License
mit
Downloads
38.1K
Likes
13
Paper
arXiv:2503.19108
Updated
2025-09-18
About tue-mps/coco_panoptic_eomt_large_640
EoMT (Encoder-only Mask Transformer) is a Vision Transformer (ViT) architecture designed for high-quality and efficient image segmentation. It was introduced in the CVPR 2025 highlight paper: Your ViT is Secretly an Image Segmentation Model by Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans, Narges Norouzi, Giuseppe Averta, Bastian Leibe, Gijs Dubbelman, and Daan de Geus.