Project for "Advanced Machine Learning" course at PoliTO. The purpose is to implement a BiSeNet able to perform real-time semantic segmentation task

Implementation of a Deep Neural Architecture to perform real-time semantic segmentation of forest fires in aerial imagery captured by drones.

Navigation based on semantic segmentation of images.

This work explores adversarial domain adaptation to enhance real-time neural networks for semantic segmentation, specifically addressing the challenges of domain shift from synthetic to real-world environments.

This repository contains research on real-time domain adaptation in semantic segmentation, aiming at bridging the gap between synthetic and real-world imagery for urban scenes and autonomous driving, utilizing STDC models and advanced domain adaptation methods.

Project for the Advanced Machine Learning course 23/24 - Politecnico di Torino

A class-based styling approach for Real-time Domain Adaptation in Semantic Segmentation

[ICIP2022] Entropy guided feature extraction for real time semantic segmentation

🏀 BasketballDetector implementation using a segmentation approach

Implement a model of real-time semantic segmentation for autonomous driving

Improved PIDNet for real-time semantic segmentation. Work in progress.

Image Segmentation Paper Review and Implementation

Oil Pollution Dataset and PIDNet

DSANet: Dilated Spatial Attention for Real-time Semantic Segmentation in Urban Street Scenes

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

Detail-Sensitive Panoramic Annular Semantic Segmentation

BiSeNetV2 implementation in TensorFlow 2.0

Pytorch code of Sequential/Hierarchical ERFNet with PSPNet for real-time semantic segmentation