Search Results for author:
Found 8 papers, 1 papers with code
Diffusion Probabilistic Multi-cue Level Set for Reducing Edge Uncertainty in Pancreas Segmentation
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.
Adversarial Training for Physics-Informed Neural Networks
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.
Re-initialization-free Level Set Method via Molecular Beam Epitaxy Equation Regularization for Image Segmentation
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.
A Review of Adversarial Attacks in Computer Vision
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.
SaaFormer: Spectral-spatial Axial Aggregation Transformer for Hyperspectral Image Classification
Consequently, the pixel-wise random sampling approach poses a risk of data leakage.
Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
Thus, we further propose an indicator to measure the local similarity of models, called robustness similitude.
Stationary Point Losses for Robust Model
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.
Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network
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.
