Try the Model

Use the widget below to experiment with Co-DETR. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

Co-Deformable-DETR (Co-DETR) is an object detection model architecture introduced in the paper "DETRs with Collaborative Hybrid Assignments Training".

On model performance, the paper abstract notes:

We conduct extensive experiments to evaluate the effectiveness of the proposed approach on DETR variants, including DAB-DETR, Deformable-DETR, and DINO-Deformable-DETR. The state-of-the-art DINO-Deformable-DETR with Swin-L can be improved from 58.5% to 59.5% AP on COCO val. Surprisingly, incorporated with ViT-L backbone, we achieve 66.0% AP on COCO test-dev and 67.9% AP on LVIS val, outperforming previous methods by clear margins with much fewer model sizes.

Co-DETR License

Co-DETR

is licensed under a

MIT License

license.

Performance

Deploy a Co-DETR API

You can use Roboflow Inference to deploy a

Co-DETR

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with Co-DETR

You can automatically label a dataset using Co-DETR with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use Co-DETR to train a computer vision model.

No items found.