6 citations · 6 across the 3 of their papers we have counts for
3 papers
Multi-Armed Bandit Approach for Optimizing Training on Synthetic Data
Abdulrahman Kerim, Leandro Soriano Marcolino, Erickson R. Nascimento +1
Supervised machine learning methods require large-scale training datasets to perform well in practice. Synthetic data has been showing great progress recently and has been used as…
Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approach
Abdulrahman Kerim, Felipe Chamone, Washington Ramos +3
Recent semantic segmentation models perform well under standard weather conditions and sufficient illumination but struggle with adverse weather conditions and nighttime. Collectin…
Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions
Abdulrahman Kerim, Washington L. S. Ramos, Leandro Soriano Marcolino +2
Video stabilization plays a central role to improve videos quality. However, despite the substantial progress made by these methods, they were, mainly, tested under standard weathe…