activity
20192023
most cited3DeformRS: Certifying Spatial Deformations on Point Clouds

5 citations · 7 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV20231 cited

Enhancing Neural Rendering Methods with Image Augmentations

Juan C. Pérez, Sara Rojas, Jesus Zarzar +1

Faithfully reconstructing 3D geometry and generating novel views of scenes are critical tasks in 3D computer vision. Despite the widespread use of image augmentations across comput…

cs.CV20225 cited

3DeformRS: Certifying Spatial Deformations on Point Clouds

Gabriel Pérez S., Juan C. Pérez, Motasem Alfarra +2

3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these model…

cs.CV20221 cited

Towards Assessing and Characterizing the Semantic Robustness of Face Recognition

Juan C. Pérez, Motasem Alfarra, Ali Thabet +2

Deep Neural Networks (DNNs) lack robustness against imperceptible perturbations to their input. Face Recognition Models (FRMs) based on DNNs inherit this vulnerability. We propose…

eess.IV2021

Generalized Real-World Super-Resolution through Adversarial Robustness

Angela Castillo, María Escobar, Juan C. Pérez +4

Real-world Super-Resolution (SR) has been traditionally tackled by first learning a specific degradation model that resembles the noise and corruption artifacts in low-resolution i…

cs.LG2021

Enhancing Adversarial Robustness via Test-time Transformation Ensembling

Juan C. Pérez, Motasem Alfarra, Guillaume Jeanneret +4

Deep learning models are prone to being fooled by imperceptible perturbations known as adversarial attacks. In this work, we study how equipping models with Test-time Transformatio…

cs.CV2021

Towards Robust General Medical Image Segmentation

Laura Daza, Juan C. Pérez, Pablo Arbeláez

The reliability of Deep Learning systems depends on their accuracy but also on their robustness against adversarial perturbations to the input data. Several attacks and defenses ha…