no code implementations • 28 Jun 2020 • Yan Min, Miles Bennett
The causal explanation of image misclassifications is an understudied niche, which can potentially provide valuable insights in model interpretability and increase prediction accuracy.
no code implementations • 29 May 2020 • Yan Min, Mao Ye, Liang Tian, Yulin Jian, Ce Zhu, Shangming Yang
Our main contributions are a novel feature section approach which uses multi-step transition probability to characterize the data structure, and three algorithms proposed from the positive and negative aspects for keeping data structure.