Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Wu, Xiaodong"'
Watermarking has become one of promising techniques to not only aid in identifying AI-generated images but also serve as a deterrent against the unethical use of these models. However, the robustness of watermarking techniques has not been extensivel
Externí odkaz:
http://arxiv.org/abs/2408.02035
Diffusion models (DPMs) have demonstrated remarkable performance in image generation, often times outperforming other generative models. Since their introduction, the powerful noise-to-image denoising pipeline has been extended to various discriminat
Externí odkaz:
http://arxiv.org/abs/2407.12952
In this paper, we study the adversarial robustness of deep neural networks for classification tasks. We look at the smallest magnitude of possible additive perturbations that can change the output of a classification algorithm. We provide a matrix-th
Externí odkaz:
http://arxiv.org/abs/2406.16200
Approximate Natural Gradient Descent (NGD) methods are an important family of optimisers for deep learning models, which use approximate Fisher information matrices to pre-condition gradients during training. The empirical Fisher (EF) method approxim
Externí odkaz:
http://arxiv.org/abs/2406.06420
Autor:
Long, Feifei, Xia, Xiangze, Liu, Jian, Liu, Zixi, Wu, Xiaodong, Wu, Xiaohe, Wan, Chenguang, Gao, Xiang, Li, Guoqiang, Luo, Zhengping, Qian, Jinping, Team, EAST
The accurate construction of tokamak equilibria, which is critical for the effective control and optimization of plasma configurations, depends on the precise distribution of magnetic fields and magnetic fluxes. Equilibrium fitting codes, such as EFI
Externí odkaz:
http://arxiv.org/abs/2403.10114
Machine teaching often involves the creation of an optimal (typically minimal) dataset to help a model (referred to as the `student') achieve specific goals given by a teacher. While abundant in the continuous domain, the studies on the effectiveness
Externí odkaz:
http://arxiv.org/abs/2401.17865
Researchers have shown significant correlations among segmented objects in various medical imaging modalities and disease related pathologies. Several studies showed that using hand crafted features for disease prediction neglects the immense possibi
Externí odkaz:
http://arxiv.org/abs/2312.12653
Diffusion models have shown impressive performance for image generation, often times outperforming other generative models. Since their introduction, researchers have extended the powerful noise-to-image denoising pipeline to discriminative tasks, in
Externí odkaz:
http://arxiv.org/abs/2312.12649
Binary semantic segmentation in computer vision is a fundamental problem. As a model-based segmentation method, the graph-cut approach was one of the most successful binary segmentation methods thanks to its global optimality guarantee of the solutio
Externí odkaz:
http://arxiv.org/abs/2312.04713
We describe a method for verifying the output of a deep neural network for medical image segmentation that is robust to several classes of random as well as worst-case perturbations i.e. adversarial attacks. This method is based on a general approach
Externí odkaz:
http://arxiv.org/abs/2310.16999