Open XFeiF opened 3 years ago
Highlight:
The proposed UP-DETR framework aims to Unsupervisedly Pre-train the transformers of DETR. The main tasks of object detection are object classification and localization. However, the DETR transformer focuses on spatial localization learning. So the problem comes that how to maintain the image classification ability. Based on this finding, the authors make the following contributions:
The entire framework:
The loss function is formed by three parts:
Paper
Code-pytorch
Authors:
Zhigang Dai, Bolun Cai, Yugeng Lin, Junying Chen
The Chinese explanation from the author Zhigang Dai in Zhihu.
The framework of the proposed UP-DETR.