This is the official repository for our recent work: PIDNet

A pytorch-based real-time segmentation model for autonomous driving

Tensorflow 2 implementation of complete pipeline for multiclass image semantic segmentation using UNet, SegNet and FCN32 architectures on Cambridge-driving Labeled Video Database (CamVid) dataset.

Semantic Segmentation using Tensorflow on popular Datasets like Ade20k, Camvid, Coco, PascalVoc

Репозиторий для обучения нейросетевых моделей по семантической сегментации + пример использования моделей на практике

Applying the 100 Layer Tiramisu on the Camvid Dataset

Official Repository for BEVANet: Bilateral Efficient Visual Attention Network for Real-time Semantic Segmentation (ICIP 2025 Spotlight Oral)

Deep learning semantic segmentation on the Camvid dataset using PyTorch FCN ResNet50 neural network.

This is the DL repository for Semantic Segmentation using U-Net model in pytorch library.

Pytorch Implementation of ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation (https://arxiv.org/abs/1606.02147)

Semantic segmentation on CamVid dataset using the U-Net.

A survey of Real time Semantic Segmentation for autonomous driving

This repository contains the official implementation of P2AT, a novel architecture designed for real-time semantic segmentation. P2AT achieves trade-off between accuracy and speed, establishing state-of-the-art results on Cityscapes and CamVid (pretrained on Cityscapes) without relying on inference acceleration techniques.

CamVid Dataset for Segmentation

Adapted representation of synthetic data to real world data.

This project was developed as a part of the presentation that I gave on the Programming 2.0 webinar: Autonomous driving.

Image Segmentation by Iterative Inference from Conditional Score Estimation

This is a project on semantic image segmentation using CamVid dataset, implemented through the FastAI framework.

🩺 Enable real-time segmentation of multimodal biomedical images with the light-weight CFPNet-M network for improved medical analysis and diagnostics.

These projects were developed as part of advanced coursework in Neural Networks and Deep Learning, focusing on cutting-edge architectures and their practical implementation for computer vision tasks.