Fatemeh Karimi
Papers
1
Total Citations
2
H-Index
1
About
Fatemeh Karimi is a researcher in computer vision and deep learning, with a focus on efficient depth estimation and learning under data constraints. Her work addresses the critical challenge of inferring 3D structure from 2D images, particularly when ground truth depth data is sparse or noisy. Her most notable contribution, "Lightdepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity Via Curriculum Learning" (2023), introduces a novel framework that leverages curriculum learning to train depth estimation models effectively despite limited labeled data. This approach prioritizes learning from easier, more reliable samples before tackling harder ones, significantly improving model robustness and resource efficiency. While her citation count is still growing, the work demonstrates a forward-thinking integration of learning strategies with practical deployment constraints, making it relevant for applications in autonomous systems, robotics, and augmented reality. Karimi’s research stands out for its emphasis on balancing accuracy with computational efficiency, a crucial consideration for real-world deployment. Her contributions are poised to influence future work in resource-constrained depth estimation, offering a pathway to more scalable and accessible 3D perception technologies.
Research Focus
Key Achievements
Top Papers
- 1