Implement Panoptic FPN to Tackle Down Panoptic Segmentation for Cityscapes Dataset

U-Net based PyTorch model for roads segmentation trained on Cityscapes dataset

Segmentation pipeline that uses a U-Net backbone to perform segmentation on the Cityscapes dataset. Conducted experiments to analyse the impact of the skip connections of the U-Net on the quality of the segmentation masks. These masks are also qualitatively analysed using the Intersection-over-Union (IoU) metric

Master Thesis, Politecnico di Milano, A. Y. 2022/23, Computer Science and Engineering

Some basic trick about semantic segmentation based on tensorflow & some open datasets

Pytorch Implementation of U-Net on Cityscapes Dataset

Camera-Invariant Domain Adaptation (Semantic Segmentation)

MTLA - Multi-Task Learning Archive

The repository contains synthetic dusk images of cityscape dataset. The datset was synthesized using UNIT GAN.

Final Project for Deep Learning Course A.Y. 2022/23. Semantic Segmentation on Cityscapes Dataset

Implementation of R2U-Net and a custom model using the main module from HANet + R2U-Net for image segmentation of urban scenes on the Cityscapes dataset

This study investigates the performance effect of using recurrent neural networks (RNNs) for semantic segmentation of urban scene images, to generate a semantic output map with refined edges. We proposed three deep neural network architectures using recurrent neural networks and evaluated them on the Cityscapes dataset. All three proposed archit…

Compact Semantic Segmentation and Depth Estimation with Multi-task Learning

This is my repository for my final project -> Semantic Segmentation of Cityscapes datasets using U-Net.

Corrupt Cityscapes Dataset

A semantic segmentation model for urban scene understanding using DashCam footage and the CityScape dataset.

The official code open source version of BFDA - based on YOLOv5

Python program to visualize Deeplab (trained on Cityscapes dataset) results.