135 datasets found

A refined night-time semantic segmentation dataset, in which the unreasonable annotations have been carefully modified in both the training and validation sets.

A large-scale night-time dataset that aims at solving the problem of inadequate training data for night-time segmentation.

A novel night-time semantic segmentation paradigm, i.e. disentangle then parse (DTP) for tackling the challenge of insufficient and complicated lighting conditions.

Extended Labeled Faces in-the-Wild (ELFW) dataset is an extension of the Labeled Faces in-the-Wild (LFW) dataset, with additional face-related categories and synthetic objects.

This paper proposes a method for semantic segmentation using point supervision.

A dataset for semantic segmentation of autonomous vehicles in real-world scenarios.

A semi-supervised active domain adaptation framework for semantic segmentation in driving scenes.

The Taskonomy dataset contains 16 types of annotation, including object classification, scene classification, depth estimation, surface normals, curvature estimation, edge...

Fluid Annotation is an intuitive human-machine collaboration interface for annotating the class label and outline of every object and background region in an image.

The dataset used for extensive cut-and-paste augmentation for unsupervised domain adaptive semantic segmentation.

The dataset used for unsupervised domain adaptation for semantic segmentation with pseudo label self-refinement.

COCO-Stuff: Thing and stuff classes in context.

A python package consisting of some well-known loss functions widely used for image segmentation.

A dataset for real-time semantic segmentation.

An urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, covering about 7.6 km2 of the city landscape.

SemanticGAN uses a dataset of real images and their corresponding semantic segmentation masks.

DatasetGAN uses a dataset of real images and their corresponding semantic segmentation masks.

Off-road image semantic segmentation is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures.

IDD dataset for Indian Road Scenarios contains 10K frames from 180 videos.

Object detection dataset used for training and testing the proposed alert system.