Bhavesh Gupta
Papers
1
Total Citations
7
H-Index
1
About
Bhavesh Gupta is a rising researcher in computer vision and medical image analysis, whose work focuses on advancing deep learning techniques for precise image segmentation. His most cited paper, "Paced-curriculum distillation with prediction and label uncertainty for image segmentation" (2023), introduces a novel framework that integrates curriculum learning with knowledge distillation, leveraging both prediction and label uncertainty to improve segmentation accuracy. This work, with 7 citations, addresses critical challenges in handling noisy or ambiguous annotations, making it particularly impactful for medical imaging applications where data quality is variable. Gupta’s contributions lie in bridging the gap between model efficiency and robustness, offering a scalable solution for real-world segmentation tasks. His research has implications for automated diagnosis and treatment planning, where reliable segmentation is paramount. As an early-career scholar, Gupta demonstrates a keen ability to tackle complex problems at the intersection of uncertainty estimation and deep learning, positioning him as a promising voice in the field. His work is already inspiring further studies in curriculum-based training paradigms, underscoring his potential to shape future advancements in computer vision and healthcare AI.
Research Focus
Key Achievements
Top Papers
- 1