activity
20242026
collaborators

9 papers

cs.CV2026

Enhancing Adversarial Robustness with Signed Distance Fields for Harmonizing Geometric Invariance and Texture

Zhe Li, Bernhard Kainz

Deep neural networks demonstrate impressive performance in visual recognition but remain highly vulnerable to imperceptible adversarial attacks. Existing defense strategies such as…

cs.CV2025

InfoMotion: A Graph-Based Approach to Video Dataset Distillation for Echocardiography

Zhe Li, Hadrien Reynaud, Alberto Gomez +1

Echocardiography plays a critical role in the diagnosis and monitoring of cardiovascular diseases as a non-invasive real-time assessment of cardiac structure and function. However,…

cs.CV2025

Label-free Motion-Conditioned Diffusion Model for Cardiac Ultrasound Synthesis

Zhe Li, Hadrien Reynaud, Johanna P Müller +1

Ultrasound echocardiography is essential for the non-invasive, real-time assessment of cardiac function, but the scarcity of labelled data, driven by privacy restrictions and the c…

cs.CV2025

Leveraging Multi-Modal Information to Enhance Dataset Distillation

Zhe Li, Hadrien Reynaud, Bernhard Kainz

Dataset distillation aims to create a small and highly representative synthetic dataset that preserves the essential information of a larger real dataset. Beyond reducing storage a…

cs.CV2025

Video Dataset Condensation with Diffusion Models

Zhe Li, Hadrien Reynaud, Mischa Dombrowski +3

In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, bot…

cs.CV2025

Graph Conditioned Diffusion for Controllable Histopathology Image Generation

Sarah Cechnicka, Matthew Baugh, Weitong Zhang +5

Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sen…