no code implementations • 15 Jan 2024 • Guoxin Wang, Sheng Shi, Shan An, Fengmei Fan, Wenshu Ge, Qi Wang, Feng Yu, Zhiren Wang
Previous research on the diagnosis of Bipolar disorder has mainly focused on resting-state functional magnetic resonance imaging.
1 code implementation • CVPR 2023 • Shenglin Yin, Kelu Yao, Sheng Shi, Yangzhou Du, Zhen Xiao
To this end, compared with standard DNNs, we discover that the generalization gap of adversarially trained DNNs is caused by the smaller attribution span on the input image.
1 code implementation • 5 Dec 2022 • Qi Wang, Sheng Shi, Jiahui Li, Wuming Jiang, Xiangde Zhang
Existing methods are limited by the inconsistent point densities of different parts in the point cloud.
Ranked #6 on Semantic Segmentation on S3DIS
no code implementations • 26 Apr 2020 • Sheng Shi, Yangzhou Du, Wei Fan
As an extension of LIME, this paper proposes an high-interpretability and high-fidelity local explanation method, known as Local Explanation using feature Dependency Sampling and Nonlinear Approximation (LEDSNA).
no code implementations • 18 Feb 2020 • Sheng Shi, Xinfeng Zhang, Wei Fan
Explainability is a gateway between Artificial Intelligence and society as the current popular deep learning models are generally weak in explaining the reasoning process and prediction results.
no code implementations • 4 Nov 2019 • Sheng Shi, Xinfeng Zhang, Wei Fan
Despite outstanding contribution to the significant progress of Artificial Intelligence (AI), deep learning models remain mostly black boxes, which are extremely weak in explainability of the reasoning process and prediction results.