visiontransformer

DSMIL: Dual-stream multiple instance learning networks for tumor detection in Whole Slide Image

Repository for Master thesis project investigating classification of 3D chest CT scans using Vision Transformer.

Vision Transformer using mlx

Deep Fake Detection using Vision Transformer and Neural Network

Experimental removal / shuffling of layers in CLIP ViT + Text Transformer

Vision transformer and CNN implementations for image classification using PyTorch.

This repository presents a radiodosiomics framework for personalized [¹⁷⁷Lu]Lu-PSMA-617 RLT in mCRPC. It includes feature selection and ML models using clinical, radiomic, and dosiomic features, plus nnU-Net and Swin UNETR DL models with SSL to predict Monte Carlo–based dose rate maps.

MPS-accelerated Brain Tumour Segmentation task based on BraTS '21 task dataset. Uses a hybrid Swin-UNETR + CNN architecture. Optimized for Apple Silicon (M-chip) systems using MPS.

The proposed system is a hybrid deep-learning architecture for landslide detection and segmentation from satellite, aerial, and drone imagery

this is tracking system designed for tracking the objects that are same visually ,this repo contains code that track the trajectories of individual objects ,count the objects at each frame and much more

Final project for the master's degree in Computer Science course "Advanced Machine Learning" (AML) at the University of Rome "La Sapienza" (A.Y. 2023-2024).

AI-Powered Multi-Crop Disease Detection & Farmer Advisory System using Vision Transformers (PyTorch & FastAPI)

Unofficial PyTorch reimplementation of OpenVision 2 for image captioning — a frozen ViT-B/16 encoder + a 6-layer GPT-style Transformer decoder with cross-attention, trained on Flickr8k. CAP6415 Computer Vision course project.

Aristotle University of Thessaloniki, Deep-Learning Project (Winter Sem. 2025-2026): Analysis of Medical Images MedMNIST with CNN, Transfer Learning & Vision Transformers (Pytorch)

This repo showcase the ENPM673: Perception for Autonomous robots final project. A vision transformer (ViT) architecture SegFormer, has been replicated for implementing semantic segmentation. Furthermore, it was deployed on raspberry pi with pi cam setup for validating the real-time performance.

Systematic review of computer vision and deep learning approaches for insect pest detection in Nepalese agriculture.

Official implementation of "A vision transformer-based approach for brain tumor detection" (CRC Press, 2024). Classifies brain MRI scans using Vision Transformers (ViT) and CNNs.

Code for the paper "Relating Implicit Bias and Adversarial Attacks through Intrinsic Dimension" [https://arxiv.org/abs/2305.15203] -- Now +CLIP!

Like Golden Gate Claude, but with a CLIP Vision Transformer ~ feature activation manipulation fun!