Deformable DETR: Deformable Transformers for End-to-End Object Detection
Abstract
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10$\times$ less training epochs. Extensive experiments on the COCO benchmark demonstrate the effectiveness of our approach. Code is released at https://github.com/fundamentalvision/Deformable-DETR.
Cite
Text
Zhu et al. "Deformable DETR: Deformable Transformers for End-to-End Object Detection." International Conference on Learning Representations, 2021.Markdown
[Zhu et al. "Deformable DETR: Deformable Transformers for End-to-End Object Detection." International Conference on Learning Representations, 2021.](https://mlanthology.org/iclr/2021/zhu2021iclr-deformable/)BibTeX
@inproceedings{zhu2021iclr-deformable,
title = {{Deformable DETR: Deformable Transformers for End-to-End Object Detection}},
author = {Zhu, Xizhou and Su, Weijie and Lu, Lewei and Li, Bin and Wang, Xiaogang and Dai, Jifeng},
booktitle = {International Conference on Learning Representations},
year = {2021},
url = {https://mlanthology.org/iclr/2021/zhu2021iclr-deformable/}
}