75 datasets found

COCO-Stuff: Thing and stuff classes in context.

A dataset for real-time semantic segmentation.

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.

The UniSeg dataset is used for multi-dataset semantic segmentation with label shifts.

The WeatherProof Dataset is a semantic segmentation dataset with accurate clear and adverse weather image pairs for better consistency loss in training and evaluation.

The FreDSNet dataset is a dataset for joint monocular depth estimation and semantic segmentation from single equirectangular panoramas.

The OmniScape dataset consists of 10,000 annotated images captured from four different view angles: Front View (FV), Mirror-View Right (MVR), Mirror-View Left (MVL), and Rear...

The SynWoodScape dataset consists of 10,000 annotated images captured from four different view angles: Front View (FV), Mirror-View Right (MVR), Mirror-View Left (MVL), and Rear...

The Vaihingen dataset consists of 1440 scenes with a size of 250×250 pixels. Each scene is a colour-infrared (CIR) true orthophoto and a height grid (digital surface model; DSM)...

Semantic segmentation is a fundamental task in computer vision and enables many downstream applications. It is related to image classification since it produces per-pixel...

Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most semantic segmentation research focuses on improving...

The Synthia dataset is a large-scale urban scene understanding dataset, containing 9000 samples. It is used for semantic segmentation tasks.

The dataset used in the paper is ADE20K for semantic segmentation.

A dataset for semantic amodal segmentation, consisting of images with semantic object labels.

The NYUD-v2 dataset is a benchmark for indoor scene segmentation and depth estimation. It contains 1449 images with 4 tasks: semantic segmentation, depth estimation, surface...

The Synthia→Cityscapes task is a domain adaptation task for semantic segmentation, where the source domain is Synthia and the target domain is Cityscapes.

The dataset used for experiments on generic image retrieval, person re-identification, and low-shot semantic segmentation.

The proposed framework for crack semantic segmentation.