no code implementations • 11 Apr 2024 • Yue Gou, Yuming Xing, Shengzhu Shi, Zhichang Guo
We use the diffusion probabilistic model in the coarse segmentation stage, with the obtained probability distribution serving as both the initial localization and prior cues for the level set method.
1 code implementation • 18 Oct 2023 • Yao Li, Shengzhu Shi, Zhichang Guo, Boying Wu
AT-PINNs enhance the robustness of PINNs by fine-tuning the model with adversarial samples, which can accurately identify model failure locations and drive the model to focus on those regions during training.
no code implementations • 13 Oct 2023 • Fanghui Song, Jiebao Sun, Shengzhu Shi, Zhichang Guo, Dazhi Zhang
This method uses the crystal growth in the MBE process to limit the evolution of the level set function, and thus can avoid the re-initialization in the evolution process and regulate the smoothness of the segmented curve.
no code implementations • 15 Aug 2023 • Yutong Zhang, Yao Li, Yin Li, Zhichang Guo
Deep neural networks have been widely used in various downstream tasks, especially those safety-critical scenario such as autonomous driving, but deep networks are often threatened by adversarial samples.
no code implementations • 29 Jun 2023 • Enzhe Zhao, Zhichang Guo, Yao Li, Dazhi Zhang
Consequently, the pixel-wise random sampling approach poses a risk of data leakage.
no code implementations • 28 Jun 2023 • Jie Ning, Jiebao Sun, Yao Li, Zhichang Guo, WangMeng Zuo
Thus, we further propose an indicator to measure the local similarity of models, called robustness similitude.
no code implementations • 19 Feb 2023 • Weiwei Gao, Dazhi Zhang, Yao Li, Zhichang Guo, Ovanes Petrosian
CE loss sharpens the neural network at the decision boundary to achieve a lower loss, rather than pushing the boundary to a more robust position.
no code implementations • 19 Nov 2022 • Xiang Wang, Yimin Yang, Zhichang Guo, Zhili Zhou, Yu Liu, Qixiang Pang, Shan Du
First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain.