Patty Coupeau
Papers
1
Total Citations
7
H-Index
1
About
Patty Coupeau is a rising researcher at the intersection of graph neural networks (GNNs) and computer vision, with a primary focus on enhancing semantic image segmentation. Her most-cited work, "On the use of GNN-based structural information to improve CNN-based semantic image segmentation" (2024, 7 citations), introduces a novel framework that leverages graph-based representations of spatial relationships to refine the output of convolutional neural networks. This contribution addresses a critical limitation in traditional segmentation models: their inability to capture long-range dependencies and global context. By integrating GNN-derived structural cues, Coupeau demonstrates how pixel-level predictions can be significantly sharpened, particularly in complex scenes with occlusions or ambiguous boundaries. Though early in her career, her work has already garnered attention for its elegant fusion of two powerful deep learning paradigms. Coupeau’s research holds promise for applications in autonomous driving, medical imaging, and robotics, where precise scene understanding is paramount. As she continues to explore the synergy between graph-based reasoning and visual perception, she is poised to become a key voice in the next generation of intelligent vision systems.
Research Focus
Key Achievements
Top Papers
- 1