Hanan Gani

vits-for-small-scale-datasets. [BMVC 2022] Official repository for "How to Train Vision Transformer on Small-scale Datasets?"

llmblueprint. [ICLR 2024] Official code for the paper "LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts"

covid19-detection. This code is for predicting COVID-19 from chest Xrays. The model currently has 95% accuracy.

MedContext. [MICCAI 2024] Official code for the paper "MedContext: Learning Contextual Cues for Efficient Volumetric Medical Segmentation"

Image-Augmentation-using-GAN. This repository contains python notebook for generating new set of images from existing images using Generative Adversarial Networks. The code has been tested on MNIST Dataset and can be extended to any other dataset

MTL-ViT. A new multi-task learning framework using Vision Transformers

channel-estimation. Python code for estimating Channel parameter in Cognitive Radio

Alzheimer-s-Detection. This repository contains code for detecting Alzheimer's patients from linguistic cues.

Multi-Task-Learning. This repo contains code and exhaustive experiments on smart multi-task learning

Covid19-ClinicalReports-Detection. This projects aims to provide a headstart to detect covid-19 from patient symptoms, clinical notes on lung xray analysis and other factors.

hananshafi.github.io. personal home page of Hanan Gani

vane-benchmark. Project page for VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs

semseg-clip. Jupyter Notebook

Unsupervised-Image-Clustering. This repository presents a python code for clustering similar images together using unsupervised approach.