Traditional Machine learning and Deep learning approaches to classify Search for extraterrestrial intelligence Signal

Kaggle Competition Bronze Medal 🥉 (205th out of 3537 teams)

This repository contains an image classification model for the subject AI Convergence and Application held on Handong Global University (HGU)

This repo hosts the water body extraction from satellite images using Trans Deeplab model.

This project includes my (31st place) solution to the 2021 Global Wheat Challenge on AICrowd. The solution is based on self-supervised learning and the Swin Transformer. The repo is forked from the original implementation of the Swin-transformer for object detection.

Comprehensive Performance Analysis of Three Pretrained Transformer Models (ViT, Swin, and MaxViT) on ImageNet and Fine-tuned on the NIH Chest X-rays Dataset for Classifying 14 Chest Radiograph Pathologies

This is a warehouse for Agent-Attention-Models based on pytorch framework, can be used to train your image datasets.

Vision Transformer

building AVA from ex-machina; a lightweight multi-modal system from scratch, just for learning & experimentation

This project uses PyTorch to classify bone fractures. As well as fine-tuning some famous CNN architectures (like VGG 19, MobileNetV3, RegNet,...), we designed our own architecture. Additionally, we used Transformer architectures (such as Vision Transformer and Swin Transformer). This dataset is Bone Fracture Multi-Region X-ray, available on Kaggle.

This is a warehouse for STL-Pytorch-model, can be used to train your image-datasets for vision tasks.

The initial stage of this work focuses on creating a segmented image from a given satellite image with different classes. In the second stage, these images should be converted to an ABM-friendly format. At the final stage, they can be used to simulate the real-world environment with related agents using a suitable Agent-based model.

A transformer model based on sliding kernel self attention mechanism. Swin Transformer's evil twin.

Implementation of a Paper related to Vision Transformer

Coursework created for the COM3025 Deep Learning And Advanced AI module during my Computer Science BSc at Surrey University

Alzheimer disease is one of the most common neuro-degenerative diseases, with an estimated 6.2 million cases in the United States. This research investigates the potential of Transformer-based deep learning techniques to accelerate the processing of diffusion tensor imaging (DTI) measures and improve the early diagnosis of AD using Sparse Data

Coursework created for the COM3001 Professional Project module during my Computer Science BSc at Surrey University

This is a warehouse for DS-TransUNet-pytorch-model, can be used to train your dataset

A Tensorflow 2.x implementation of focal transformer

A Framework for Real-time Object Detection and Image Restoration