168 datasets found

Unsupervised domain adaptation for semantic segmentation via class-balanced self-training

The proposed DualPyramidGenerativeAdversarialNetworks for semantic image synthesis

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.

Semantic scene segmentation of urban scenes captured from the Unmanned Aerial Vehicles (UAV) perspective plays a vital role in building a perception model for UAV.

Semantic scene segmentation of urban scenes captured from the Unmanned Aerial Vehicles (UAV) perspective plays a vital role in building a perception model for UAV.

Semantic scene segmentation of urban scenes captured from the Unmanned Aerial Vehicles (UAV) perspective plays a vital role in building a perception model for UAV.

The PASCAL VOC12 dataset is a semantic segmentation dataset.

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 CANet dataset is a benchmark for few-shot semantic segmentation.

The PANet dataset is a benchmark for few-shot semantic segmentation.

The proposed Semantic Meta-Learning (SML) framework for few-shot semantic segmentation.

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.

Semantic segmentation is a critical computer vision component of autonomous navigation and robotic systems. It involves dense and high dimensional prediction of a label for...