Jean-Luc Watson

Jean-Luc is a Research Scientist on NVIDIA's Security and Privacy research team, building new frameworks and tools for secure and private systems that can leverage hardware and cryptographic guarantees.

Chaz Gouert

Chaz joined the Programming Systems and Applications research group as a Research Scientist at NVIDIA in 2024. He completed his Ph.D. in computer engineering at the University of Delaware, where his research focused on usability and acceleration of fully homomorphic encryption schemes. As a Research Intern, he contributed to projects focused on accelerating end-to-end applications over encrypted data on multi-GPU systems. His research interests include privacy-enhancing technologies, applied cryptography, and all other aspects of cybersecurity. 

Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation

Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing pseudo masks for training segmentation models by refining CAM-like heatmaps. However, the produced heatmaps may capture only the discriminative image regions of object categories or the associated co-occurring backgrounds.