activity
20192023
most citedOnline Distillation with Continual Learning for Cyclic Domain Shifts

7 citations · 21 across the 11 of their papers we have counts for

collaborators
Showing 2022Show all

7 papers · 1 filter

cs.CV2022

PIVOT: Prompting for Video Continual Learning

Andrés Villa, Juan León Alcázar, Motasem Alfarra +5

Modern machine learning pipelines are limited due to data availability, storage quotas, privacy regulations, and expensive annotation processes. These constraints make it difficult…

cs.CV2022★ 3 cited

SimCS: Simulation for Domain Incremental Online Continual Segmentation

Motasem Alfarra, Zhipeng Cai, Adel Bibi +2

Continual Learning is a step towards lifelong intelligence where models continuously learn from recently collected data without forgetting previous knowledge. Existing continual le…

cs.LG2022★ 1 cited

Generalizability of Adversarial Robustness Under Distribution Shifts

Kumail Alhamoud, Hasan Abed Al Kader Hammoud, Motasem Alfarra +1

Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations of DN…

cs.LG2022★ 1 cited

Certified Robustness in Federated Learning

Motasem Alfarra, Juan C. Pérez, Egor Shulgin +2

Federated learning has recently gained significant attention and popularity due to its effectiveness in training machine learning models on distributed data privately. However, as…

cs.CV2022★ 5 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.CV2022★ 1 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…