arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.12329cs.CV
收藏

DAB-DETR:动态锚框更适合DETR

DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

Tsinghua University(清华大学);International Digital Economy Academy (IDEA)(国际数字经济研究院(IDEA));Hong Kong University of Science and Technology(香港科技大学);Peng Cheng Laboratory(鹏城实验室)

Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, Lei Zhang

摘要:

在本文中,我们提出了一种新的查询公式使用动态锚框DETR(检测Transformer),并提供了一个更深入的了解查询中的作用DETR。这种新的公式直接使用框坐标作为Transformer解码器中的查询,并逐层动态更新它们。使用框坐标不仅有助于使用显式的位置先验来提高查询到特征的相似性并消除DETR中训练收敛缓慢的问题,而且还允许我们使用框的宽度和高度信息来调节位置注意力图。这样的设计清楚地表明,DETR中的查询可以实现为以级联方式逐层执行软ROI池化。因此,在相同的设置下,它在类似DETR的检测模型中在MS-COCO基准测试中具有最佳性能,例如,AP 45.7\%使用ResNet 50-DC 5作为50 epochs训练的骨干。我们还进行了大量的实验,以证实我们的分析和验证我们的方法的有效性。代码可在\url{https://github.com/SlongLiu/DAB-DETR}上获得。

英文摘要:

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in Transformer decoders and dynamically updates them layer-by-layer. Using box coordinates not only helps using explicit positional priors to improve the query-to-feature similarity and eliminate the slow training convergence issue in DETR, but also allows us to modulate the positional attention map using the box width and height information. Such a design makes it clear that queries in DETR can be implemented as performing soft ROI pooling layer-by-layer in a cascade manner. As a result, it leads to the best performance on MS-COCO benchmark among the DETR-like detection models under the same setting, e.g., AP 45.7\% using ResNet50-DC5 as backbone trained in 50 epochs. We also conducted extensive experiments to confirm our analysis and verify the effectiveness of our methods. Code is available at \url{https://github.com/SlongLiu/DAB-DETR}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑