activity
20242026
collaborators

7 papers

cs.CV2026

Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks

Ei Hmue Khine, Yao Li, Jiebao Sun +3

While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations. Pixel-wise attacks frequently introd…

cs.CV2026

SILSM: A Sustainable Interactive Level Set Method for Progressive Refinement

Jiachen Song, Dazhi Zhang, Fanghui Song +2

Interactive segmentation aims to precisely isolate target objects using sparse user guidance. However, traditional methods often suffer from heavy interaction burdens and parameter…

cs.LG2025

PINNsFailureRegion Localization and Refinement through White-box AdversarialAttack

Shengzhu Shi, Yao Li, Zhichang Guo +2

Physics-informed neural networks (PINNs) have shown great promise in solving partial differential equations (PDEs). However, vanilla PINNs often face challenges when solving comple…

cs.CV2025

TA-LSDiff:Topology-Aware Diffusion Guided by a Level Set Energy for Pancreas Segmentation

Yue Gou, Fanghui Song, Yuming Xing +3

Pancreas segmentation in medical image processing is a persistent challenge due to its small size, low contrast against adjacent tissues, and significant topological variations. Tr…

cs.CV2024

Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling

Jie Ning, Jiebao Sun, Shengzhu Shi +4

Deep learning-based image denoising models demonstrate remarkable performance, but their lack of robustness analysis remains a significant concern. A major issue is that these mode…

cs.CV2024

Re-initialization-free Level Set Method via Molecular Beam Epitaxy Equation Regularization for Image Segmentation

Fanghui Song, Jiebao Sun, Shengzhu Shi +2

Variational level set method has become a powerful tool in image segmentation due to its ability to handle complex topological changes and maintain continuity and smoothness in the…