|
I am a CSE graduate student at University of California San Diego. I am currently working under Prof. Mikhail (Misha) Belkin. Prior to this, I was a Project Assistant at the Vision and AI Lab (VAL), Indian Institute of Science, under Prof. R. Venkatesh Babu, where I worked on Multi-Modal Learning and Vision-Language Models. I completed B.Tech in CSE from IIIT Guwahati, where I secured departmental rank 2. I did my Bachelor's thesis under the supervision of Prof. C. V. Jawahar on the topic of Semantic segmentation for the urban road settings using Diffusion Models. In the summer of 2022, I participated in the Parameterized Algorithms and Computational Experiments (PACE) competition under the guidance of Dr. Srinibas Swain and secured Global Rank 1, in the heuristic track. Email / CV / LinkedIn / Google Scholar / Github |
|
|
|
|
|
|
|
Srijan Das, Tanmay Jain, Dominick Reilly, Pranav Balaji, Soumyajit Karmakar, Shyam Marjit, Xiang Li, Abhijit Das, and Michael S. Ryoo. Winter Conference on Applications of Computer Vision (WACV), 2024 arXiv / code We developed a joint ViT training pipeline which uses a Self-Supervised Auxiliary Task alongside the primary task, for when the training data is limited. |
|
|
|
|
Soumyajit Karmakar, Abeer Banerjee, Prashant Sadashiv Gidde, Sumeet Saurav, and Sanjay Singh. Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) 2022 arXiv / code We developed a novel convolution stacking based ensemble learning technique that can efficiently extract and process the knowledge base of various pretrained CNN networks. |
|
Aman Jain, Sachin Agarwal, Nimish Agrawal, Soumyajit Karmakar, Srinibas Swain. Poster session of the International Symposium on Parameterized and Exact Computation (IPEC), 2022 arXiv / code Our submission for the PACE 2022 competition. We developed a novel divide and conquer heuristic algorithm to obtain the Directed Feedback Vertex Set of a graph. |
|
|
|
|