Sayak Chakraborty

Papers

Total Citations

H-Index

About

Sayak Chakraborty is a computer vision researcher specializing in semantic segmentation, where his work bridges classical statistical methods and modern deep learning architectures. His most cited paper, "Two Stage Semantic Segmentation by SEEDS and Fork Net" (2020, 4 citations), introduces a hybrid approach that combines the computational efficiency of SEEDS superpixel algorithms with the representational power of ForkNet-style deep networks. This two-stage framework addresses a critical challenge: while statistical methods struggle with complex natural environments, purely deep learning approaches often demand prohibitive computational resources. By integrating both paradigms, Chakraborty demonstrates how to achieve robust pixel-level labeling without sacrificing efficiency. His research contributes to making semantic segmentation more practical for real-world applications, particularly in resource-constrained settings. Though early in his career, his work reflects a thoughtful synthesis of traditional and contemporary techniques, offering a pathway for deploying advanced computer vision in diverse, uncontrolled environments. Chakraborty’s focus on balancing accuracy and computational cost positions him as a promising voice in the ongoing evolution of scene understanding technologies.