madhusaran26,Madhumitha Saravanan,github

🚀 I'm Madhumitha, a Computer Science Master's candidate at Arizona State University set to graduate in May 2024, specializing in Computer Vision and Deep Learning. My passion lies in pushing the boundaries of AI and data science.

🔬 With a strong foundation in designing object detection and tracking models, I've contributed to firearm and suspicious aircraft detection projects at Teuvonet. At Siemens, I enhanced anomaly and object detection using foundational models.

📊 In my corporate career, I designed machine learning backed product launch models, forecasting drug placement in evolving therapies, consumer response analysis through text mining and so on for pharmaceuticals, thus boosting success rates significantly. As a data scientist, I led teams, managed tight deadlines, and contributed to business development through research POCs and project pitches.

🌟 As a first-generation graduate student, I'm proactive in learning and committed to advancing technology. I'm currently seeking full-time roles starting in May 2024 as a Machine Learning Engineer, Deep Learning Engineer, Computer Vision Engineer, Data Scientist, or Applied Scientist.

Madhumitha Saravanan's Projects

benchmarktransformers

Expanding the benchmarking to CT Pulmonary Embolism Analysis

biomedicalimageanalysis

This repository contains the notebook used in the analysis of Chest X-ray datasets, and the polyp segmentation of ASU Mayo Clinic dataset.

clip-driven-universal-model

[ICCV 2023] CLIP-Driven Universal Model; Rank first in MSD Competition.

madhusaran26

Config files for my GitHub profile.

mednext

MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation (MICCAI 2023).

stu-net

The largest pre-trained medical image segmentation model (1.4B parameters) based on the largest public dataset (>100k annotations), up until April 2023.

swin-transformer-object-detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

swin-transformer-semantic-segmentation

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

torchdistill

A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆20 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.