Tashmoy Ghosh
Papers
1
Total Citations
2
H-Index
1
About
Tashmoy Ghosh is an emerging researcher specializing in computer vision and deep learning, with a particular focus on image enhancement and generative adversarial networks (GANs). His most notable work centers on underwater image processing, where he has made meaningful contributions to addressing one of the field's persistent challenges — restoring visual clarity in degraded aquatic imagery. In his paper "Separated Attention: An Improved Cycle GAN Based Underwater Image Enhancement Method" (2024), Ghosh proposed an innovative modification to the widely recognized Cycle GAN architecture, introducing depth-oriented attention mechanisms into the loss function to significantly improve contrast and image quality in underwater conditions. This work demonstrates his ability to thoughtfully build upon state-of-the-art generative models and adapt them to specialized real-world applications. Though early in his research career with 2 citations to date, Ghosh's work reflects a strong grasp of cutting-edge techniques in unsupervised image-to-image translation and attention-based deep learning. His research holds promising implications for fields such as marine exploration, underwater robotics, and aquatic surveillance, positioning him as a researcher to watch as his contributions continue to develop and gain recognition within the community.
Research Focus
Key Achievements
Top Papers
- 1