Detection Transformers with Assignment

By Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl

TL; DR. Detection Transformers with Assignment (DETA) re-introduce IoU assignment and NMS for transformer-based detectors. DETA trains and tests comparibly as fast as Deformable-DETR and converges much faster (50.2 mAP in 12 epochs on COCO).

Downloads last month: 14

Safetensors

Model size

219M params

Tensor type

I64

F32

Inference Examples

Object Detection

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.