Sai Mitheran Jagadesh Kumar

I am a recent graduate from Carnegie Mellon University, majoring in Electrical and Computer Engineering, specializing in AI/ML systems. I graduated from National Institute of Technology, Tiruchirappalli in 2022 as a Gold medalist in Electronics and Communication Engineering. I was affiliated with the Max Planck Institute of Informatics, Saarbrücken, funded by the DAAD-WISE Scholarship.

I'm a recipient of the Indian Academy of Sciences Research Fellowship, the prestigious Dr. A.L. Abdussattar Memorial Award, the Sri Janardhana Iyengar Memorial Award, and the Graphics Replicability Stamp Award. Outside of research, I'm open to anything to do with Sustainability and Mental Health. Scroll down to know more!

Linktree  /  Email  /  Personal Email  /  LinkedIn  /  GitHub

I collaborated with researchers at the Medical Mechatronics Lab, National University of Singapore, as a Research Assistant to work on Graph-based Deep Reasoning and Surgical Scene Understanding. As a Deep Learning Engineer at AIMonk Labs Pvt. Ltd. I worked in a team of five to build Neuralmarker, transforming businesses with Computer Vision. I received a recommendation from Foxconn Country Head, Josh Foulger, to work with their Intelligent Systems Team on prototyping.

Previously, I was affiliated with the Advanced Geometric Computing Lab and the Shakti Group, Indian Institute of Technology, Madras. I was supervised by Dr. M. Ramanathan and Dr. V. Kamakoti, the Director of IIT-M. I've worked on Deep Generative Modelling of Real-time Wireless Communication Channels using UAVs, with Dr. E.S Gopi, Pattern Recognition Lab NIT Trichy, and Dr. Nalin Jayakody, the Director of the Tomsk Infocomm Lab.

Now that you've kept reading till here, check out the work done by my amazing research group at The Learning Machines.

Our work introduces a framework for compressing Vision Transformer models for efficient segmentation, with a focus on enabling deployment on resource-constrained devices like the NVIDIA Jetson Nano (4GB). Our approach combines structured pruning, distillation from a stronger teacher, and quantization strategies to significantly reduce memory usage and inference latency while maintaining high segmentation accuracy and mean IoU. This allows for the rapid deployment of Vision Transformers on the edge.

This work develops a detector-free gradient-based localized feature extraction approach that enables end-to-end model training for downstream surgical tasks such as report generation and tool-tissue interaction graph prediction. We eliminate the need for object detection or region proposal and feature extraction networks by extracting the features of interest from the discriminative regions in the feature map of the classification models. Here, the discriminative regions are localized using gradient-based localization techniques (e.g. Grad-CAM). We show that our proposed approaches enable the real-time deployment of end-to-end models for surgical downstream tasks.

This work introduces a simple, lightweight, and efficient framework for single-image haze removal, exploiting rich “dark-knowledge" information from a lightweight pre-trained super-resolution model via the notion of heterogeneous knowledge distillation.

The Lottery Ticket Hypothesis (LTH) states that for a reasonably sized neural network, there exists a subnetwork within the same network that, when trained from the same initialization, yields no less performance than the dense counterpart. We investigate the effect of model size and the ease of finding winning tickets. Through this work, we show that winning tickets is in-fact, easier to find for smaller models.

This paper introduces a globally-reasoned multi-task surgical scene understanding model capable of performing instrument segmentation and tool-tissue interaction detection.

In this work, we introduce an architecture, Audiomer, where we combine 1D Residual Networks with Performer Attention to achieve state-of-the-art performance in Keyword Spotting with raw audio waveforms, out-performing all previous methods while also being computationally cheaper and parameter-efficient.

We propose using a Transformer in combination with a target attentive GNN, which allows richer Representation Learning. We outperform the existing methods on real-world benchmark datasets.

This article presents the procedure and results of a web application made to visualize field lines of Electric and Magnetic waves inside a waveguide. We propose a first-of-the-kind Graphical User Interface for waveguide visualization as a public resource.

We introduce the CADSketchNet dataset, an annotated collection of sketches of 3D CAD models, which is intended to enhance the research on developing AI-enabled search engines for 3D CAD models. We also evaluate the performance of various retrieval systems. Many experimental models are constructed and tested on CADSketchNet.