Yunyi Xuan — accepted AI-conference papers

2022

Label Matching Semi-Supervised Object Detection

Binbin Chen, Weijie Chen, Shicai Yang, Yunyi Xuan, Jie Song, Di Xie +3

CVPR 2022poster

Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to severe confirmation bias during self-training. In this paper…

Cited by 95 PDF ↗code ↗Scholar ↗

2022

Simulation-and-Mining: Towards Accurate Source-Free Unsupervised Domain Adaptive Object Detection

Peng Yuan, Weijie Chen, Shicai Yang, Yunyi Xuan, Di Xie, Yueting Zhuang +1

ICASSP 2022accepted

Vanilla unsupervised domain adaptive (UDA) object detection typically requires the labeled source data for joint-training with the unlabeled target data, which is usually unavailable in real-world scenarios due to data privacy, leading to source data-free UDA object detection. Herein, we first analy…

Cited by 0 Source ↗Scholar ↗