BriefGPT.xyz
Oct, 2020
Deformable DETR：可变形Transformer完整目标检测
Deformable DETR: Deformable Transformers for End-to-End Object Detection
HTML
PDF
Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang...
TL;DR
Deformable DETR提出了一种改进的Transformer注意力模块，只关注于围绕参考点的一小集采样点，能够更好地实现物体检测，尤其是在小物体上，并在COCO基准测试上得到了有效的实验结果。
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 spat
→