no code implementations • ICLR 2019 • Benyuan Sun, Yizhou Wang
Training hard examples aggravates the distribution shifting and damages the training.
no code implementations • 3 Aug 2022 • Benyuan Sun, Jin Dai, Zihao Liang, Congying Liu, Yi Yang, Bo Bai
SIMT lays the foundation of pre-training with large-scale multi-task multi-domain datasets and is proved essential for stable training in our GPPF experiments.
no code implementations • NeurIPS 2021 • Benyuan Sun, Hongxing Huo, Yi Yang, Bo Bai
The superiority of our algorithm is proved by demonstrating the new state-of-the-art results on cross-domain federated classification and detection.
no code implementations • 21 Jul 2018 • Benyuan Sun, Zhen Zhou, Fandong Zhang, Xiuli Li, Yizhou Wang
Meanwhile, our sampling strategy halves the training time of the proposal network on LUNA16.
5 code implementations • 2 Jun 2016 • Yunzhu Li, Benyuan Sun, Tianfu Wu, Yizhou Wang
The proposed method addresses two issues in adapting state- of-the-art generic object detection ConvNets (e. g., faster R-CNN) for face detection: (i) One is to eliminate the heuristic design of prede- fined anchor boxes in the region proposals network (RPN) by exploit- ing a 3D mean face model.
Ranked #7 on Face Detection on Annotated Faces in the Wild