Computer Vision Experimentation Frameworks - Semantic Segmentation

This repository contains an easy-to-use and flexibly customizable framework for developing and training semantic segmentation models. The focus was put on being usable out-of-the-box, without being a black box and giving the possibility to be adapted to individual projects. Therefore several features like pre-trained state-of-the-art models are already provided for fast and efficient development. The intended use of this repository is to solve various 2D segmentation problems.
In addition, we provide extensive example experiments on Cityscapes and PASCAL VOC. Our results provide valuable insights into the different features of our framework and their impact on segmentation performance.

Computer Vision Experimentation Frameworks © Karol Gotkowski

Find Computer Vision Experimentation Frameworks - Semantic Segmentation on Helmholtz Imaging Connect
Authors: Lars Krämer