This is the project website for Generative Counterfactual Augmentation ICCVW 2025

This is the PyTorch implementation of Latent Counterfactual Augmentations

This repository is collection of computer vision related papers I've read during my PhD. This will act as collection of papers I found interesting and could potential be used as a reference

This repository is code for debiasing large chest X-ray datasets using StyleGAN3. We use code from HiddenInPlainSight repository to demonstrate our methods robustness agains adversarial attacks

This is an implementation of GCA for real-time data augmentation using foundation models embeddings

This is the implementation of our Diffusion based Generative Counterfactual Augmentation Framework

This is the pytorch version of previously proposed GCA algorithm. Debiasing large chest X-ray datasets using StyleGAN3. We use code from HiddenInPlainSight repository to demonstrate our methods rob…

We use a cheXplain autoencoder architecture to encoder real chest x-ray images for counterfactual image generation

This repository detects tooth cavities using publicly available mouth x-rays and yolo models for disease, mouth quadrant, and tooth detection. We aggregate all model outputs for more information to…

Scratch is a mobile app for pool players of all levels to track, visualize, and empower their gameplay. My hope for this project is to showcase AI's ability to keep track of pool gameplay. In the f…

This repository is code for debiasing large chest X-ray datasets using StyleGAN3. We use code from HiddenInPlainSight repository to demonstrate our methods robustness agains adversarial attacks

MS Lesion Tracking with unsupervised learning methods. Used Non-Linear Dimensionality Reduction Techniques to track MS lesions in Brain MRI images

We propose a framework for registration and segmentation of image pairs using patch-based convolutional neural networks

The goal of this project is to leverage works from LABEL-FREE CONCEPT BOTTLENECK MODELS, Oikarinen et al, 2023 & Language in a Bottle, Yang et al, 2023

This goal of this project is to propose a novel method for fast medical image-to-image (I2I) synthesis. So far, I've accomplished the following tasks: (1) performed I2I synthesis using Brownian Bri…

In this experiment we see if KAN can truly outperform MLP in segmentation tasks.

This is the implementation of Diffusion Model for Active Lesion Prediction (DALP) accepted for poster presentation at ISBI 2024

A deep learning approach to tracking MS lesions in Brain MR Images

They Idea of this project is to predict whether or not a patient is likely to have a stroke based on pre and post stroke images.

List of papers read during my PhD separated by year read, year published, topic, and relevance to my research