OneFormer vs. MobileNet SSD v2: Compared and Contrasted

Models

OneFormer is a state-of-the-art multi-task image segmentation framework that is implemented using transformers.

This architecture provides good realtime results on limited compute. It's designed to run in realtime (30 frames per second) even on mobile devices.

Model Type

Instance Segmentation

Object Detection

Model Features

Item 1 Info

Item 2 Info

Architecture

Transformers

Frameworks

PyTorch

TensorFlow 1.5

Annotation Format

Instance Segmentation

GitHub

GitHub Stars

1.3k+

81+

License

MIT

Paper

Training Notebook

Deploy Model

Provide your own image below to test YOLOv8 and YOLOv9 model checkpoints trained on the Microsoft COCO dataset.

COCO can detect 80 common objects, including cats, cell phones, and cars.