Detection Transformers with Assignment

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

From the paper NMS Strikes Back.

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
9
Safetensors
Model size
48.5M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for jozhang97/deta-resnet-50-24-epochs

Finetunes
1 model

Spaces using jozhang97/deta-resnet-50-24-epochs 2