no code implementations • 21 May 2024 • Yihong Huang, Yuang Zhang, Liping Wang, Fan Zhang, Xuemin Lin
Most deep UOD models are trained exclusively on clean datasets to learn the distribution of the normal data, which requires huge manual efforts to clean the real-world data if possible.
1 code implementation • 26 May 2023 • Yihong Huang, Yuang Zhang, Liping Wang, Xuemin Lin
To our knowledge, our approach is the first to enable reliable identification of the optimal training iteration during training without requiring any labels.
1 code implementation • 24 Oct 2022 • Yihong Huang, Liping Wang, Fan Zhang, Xuemin Lin
In addition, we observe that existing algorithms have a performance drop with the mitigated data leakage issue.