Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Comparative Study of CNN and Vision Transformer architectures for high-resolution semantic segmentation.

A modular, extensible, and production-ready framework for 3D CT scan segmentation using PyTorch Lightning, TorchIO, and modern deep learning best practices which supports preprocessing, training, prediction, and evaluation for medical image segmentation tasks.

AI-Powered Image Segmentation System - Production-ready computer vision application with SegFormer + UNet models, Azure Functions backend, and beautiful visualization

AI clothing detection API with segmentation, background removal, and color analysis. Built with FastAPI + Segformer.

Repository of the paper: RailSafeNet: Visual Scene Understanding for Tram Safety

This repository contains implementations of road segmentation models using deep learning techniques. The primary goal is to accurately identify drivable road areas in images captured from a vehicle's perspective.

AI Pipeline that is truly free, and doesnt require and internet connection to use. Built and Optimized for use with Acer Predator Helios Neo 16 w/RTX4060

A machine learning project designed to detect road damage from images, leveraging deep learning and computer vision techniques for efficient and accurate damage detection.

An application for automatic road damage assessment using semantic segmentation on high-resolution images. The project helps municipal authorities and maintenance teams detect and prioritize road repairs, improving safety and reducing costs.

This repository implements and compares deep learning models for semantic segmentation using the Oxford-IIIT Pet and Cityscapes datasets.

Semantic Segmentation of Drone Images With Hugging Face and MLflow

This is a warehouse for SegFormer-pytorch-model, can be used to train your image datasets for segmentation tasks.

Tackling the challenges of off-road environment navigation through Attention Guided Off-Road Semantic Segmentation.

PyTorch and TensorFlow/Keras image models with automatic weight conversions and equal API/implementations - Vision Transformer (ViT), ResNetV2, EfficientNetV2, NeRF, SegFormer, MixTransformer, (planned...) DeepLabV3+, ConvNeXtV2, YOLO, etc.

A repository of SegFormer model test

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.

This repository provides an overview of Segformer, architecture encoder in particular. Some details of Segformer can be misleaded, thus makes a short description here to help understand the model. Meanwhile, the code (Keras/TensorFlow) is also provided for supporting.

PyTorch Implementation of SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers