135 datasets found

The Argoverse dataset is a large-scale dataset for autonomous driving, containing 3D point clouds, semantic segmentation masks, and instance segmentation masks.

A dataset of textual entailment tasks, used for evaluating the ability of language models to understand relationships between texts.

The proposed framework for leveraging the semantic segment without transferring any extra bit.

HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image

CelebAMask-HQ provides the parsing map of images in CelebA-HQ down-sampled to 512 × 512, where pixel-level annotation of 19 classes, including facial components and accessories,...

The dataset used for the experiments with the proposed approach to augment image data for semantic segmentation networks by applying image-to-image translation with both, a...

A retinal fundus glaucoma challenge dataset.

The BRATS18 multi-modal brain tumor dataset is used for training and testing the proposed TC-MGAN model.

The dataset used in the paper is Argoverse-HD, Cityscapes, and nuScenes.

PASCAL VOC 2007 dataset is a widely used dataset for object detection and semantic segmentation. We use all the split sets (training, validation, testing) in the VOC2007 dataset...

This dataset is used for semantic segmentation of bitewing radiography images. The goal is to segment the images into caries, enamel, dentin, pulp, crowns, restoration and root...

A point cloud dataset with large quantity of dynamic instances, consisting of 2,988 real-world scans with point-level annotations.

The LoveDA dataset contains high-spatial-resolution images from three different cities, focusing on improving the generalization capability of model from different urban and...

Vehicle detection in real-time is a challenging and important task. The existing real-time vehicle detection lacks accuracy and speed. Real-time systems must detect and locate...

Semantic segmentation of remote sensing imagery generally revolves two primary approaches: pixel-based and object-based methods.

The ISPRS Vaihingen dataset consists of remotely sensed imagery with a spatial resolution of 9 centimeters, and includes 6 semantic classes.

Semantic segmentation is a crucial and challenging task for image understanding. It aims to predict a dense labeling map for the input image, which assigns each pixel a unique...

The S3DIS and ScanNet datasets are used for point cloud semantic segmentation.

The TrashNet dataset contains images of waste, focusing on recycling waste classification.

Human parsing aims to segment a human image into multiple semantic parts. It is a pixel-level prediction task which requires to understand human images in both the global level...