wentacc/Bayesian-Segmentation-and-Uncertainty-estimation-on-CityScapes
Implement a network for semantic segmentation in image data, and also generate estimates of aleatoric and epistemic uncertainties associated with the segmentation.
This project helps computer vision engineers and researchers accurately identify and categorize different objects within urban street scenes. It takes in raw image data of cityscapes and outputs a segmented image where each pixel is classified (e.g., road, building, pedestrian), along with estimates of how certain the classification is. This allows you to understand not just what's in an image, but also where the system might be unsure.
113 stars. No commits in the last 6 months.
Use this if you need to perform precise object recognition in complex urban environments and want to quantify the reliability of your segmentation results.
Not ideal if your primary need is general image classification or object detection without detailed pixel-level segmentation or uncertainty quantification.
Stars
113
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/wentacc/Bayesian-Segmentation-and-Uncertainty-estimation-on-CityScapes"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MLSTRUCT/MLStructFP
Multi-unit floor plan dataset for architectural analysis and recognition
yassouali/pytorch-segmentation
:art: Semantic segmentation models, datasets and losses implemented in PyTorch.
wkentaro/pytorch-fcn
PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original...
meetps/pytorch-semseg
Semantic Segmentation Architectures Implemented in PyTorch
fregu856/deeplabv3
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.