Z
Zhuoran Yu
Researcher at SenseTime
Publications - 3
Citations - 105
Zhuoran Yu is an academic researcher from SenseTime. The author has contributed to research in topics: Convolution & Object detection. The author has an hindex of 2, co-authored 2 publications receiving 41 citations.
Papers
More filters
Proceedings ArticleDOI
Scale-Equalizing Pyramid Convolution for Object Detection
TL;DR: Jeon et al. as mentioned in this paper proposed a scale-equalizing pyramid convolution (SEPC) that aligns the shared pyramid convolutions kernel only at high-level feature maps to extract scale-invariant features.
Posted Content
Scale-Equalizing Pyramid Convolution for Object Detection
TL;DR: A scale-equalizing pyramid Convolution (SEPC) that aligns the shared pyramid convolution kernel only at high-level feature maps is built, which brings significant performance improvement in state-of-the-art one-stage object detectors and a light version of SEPC also has ~3.5AP gain with only around 7% inference time increase.
Proceedings ArticleDOI
Group R-CNN for Weakly Semi-supervised Object Detection with Points
TL;DR: Group R-CNN significantly outperforms the prior method Point DETR by 3.9 mAP with 5% well-labeled images, which is the most challenging scenario, and is also the most effective method on the MS-COCO benchmark.