4 citations · 4 across the 2 of their papers we have counts for
2 papers
cs.CV2020
Decoupled Self Attention for Accurate One Stage Object Detection
Kehe WU, Zuge Chen, Qi MA +2
As the scale of object detection dataset is smaller than that of image recognition dataset ImageNet, transfer learning has become a basic training method for deep learning object d…
cs.CV2020★ 4 cited
Improvement of Classification in One-Stage Detector
Wu Kehe, Chen Zuge, Zhang Xiaoliang +1
RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the pre…