no code implementations • 22 Jun 2022 • Liu Zhendong, Wenyu Jiang, Yi Zhang, Chongjun Wang
With the rapid development of eXplainable Artificial Intelligence (XAI), a long line of past work has shown concerns about the Out-of-Distribution (OOD) problem in perturbation-based post-hoc XAI models and explanations are socially misaligned.