# Deformable attention mechanism

Object detection model trained on the LVIS dataset containing 1,203 categories using deformable detection transformer architecture

Deformable DETR is an end-to-end object detection model that improves detection performance using Transformer architecture and deformable attention mechanisms.

The Deformable DETR single-scale model, designed for object detection tasks, employs end-to-end training and demonstrates excellent performance on the COCO 2017 dataset.

Deformable DETR is an end-to-end object detection model that combines the advantages of Transformer architecture and deformable convolution, achieving efficient object detection on the COCO dataset.

Deformable DETR is a Transformer-based object detection model that enables end-to-end training through bounding box refinement and two-stage detection, suitable for the COCO dataset.

Deformable DETR is an end-to-end object detection model that combines the advantages of Transformer architecture and deformable convolution, trained on the COCO dataset.