40 datasets found

Tags: Semantic Segmentation

Filter Results
  • PST900

    The PST900 dataset is a benchmark for RGB-Thermal semantic segmentation, containing 894 synchronized and calibrated RGB and thermal image pairs with pixel-level human annotations.
  • PASCAL-5i

    Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature...
  • GTA

    The GTA dataset consists of 24966 synthetic images synthetically generated from a video game consisting of outdoor scenes with rich variety of variations in lighting and traffic...
  • Inria Aerial Image Labeling Data Set

    Semantic segmentation in high resolution remote sensing images
  • ISPRS Potsdam Semantic Labeling data set

    Semantic segmentation in high resolution remote sensing images
  • NYUD-v2

    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...
  • Street View

    Street View is a large-scale dataset of 3D scenes, consisting of millions of images taken from street-level cameras.
  • Foggy Cityscapes

    The Foggy Cityscapes dataset is an extension to the Cityscapes dataset, containing 5k diverse real-world urban driving scenes with fog.
  • COCO-20i, FSS-1000, and LVIS-92i

    The dataset used for one-shot semantic segmentation, including COCO-20i, FSS-1000, and LVIS-92i.
  • Gaofen dataset

    The Gaofen dataset is a high-quality PolSAR semantic segmentation dataset.
  • ADE20K Dataset

    The ADE20K dataset is a large-scale dataset for semantic segmentation. It contains 20,000 images with 150 semantic categories, with 20,000 images for training, 2,000 images for...
  • ICNet for Real-Time Semantic Segmentation

    Real-time semantic segmentation system for high-resolution images
  • CamVid Dataset

    CamVid dataset is a benchmark dataset for semantic segmentation. It consists of 700 images with 11 object classes.
  • UAVid Dataset

    UAVid is a dataset for semantic segmentation of UAV images, containing 420 images with 8 classes.
  • Pascal VOC 2012

    The dataset used in the paper is the Pascal VOC 2012 dataset, which is a benchmark for instance segmentation. The dataset consists of 1464 images with 20 class categories and...
  • COCO Stuff

    COCO Stuff dataset is an extension of the COCO dataset, 164,000 images covering 171 classes are annotated with segmentation masks.
  • Pyramid scene parsing network

    Pyramid scene parsing network for semantic segmentation.
  • PASCAL Context

    The PASCAL Context dataset is a benchmark for multi-task learning in computer vision. It contains 10103 images with 5 tasks: semantic segmentation, human body part segmentation,...
  • OneFormer

    OneFormer is a universal image segmentation framework jointly trained on the panoptic, semantic, and instance segmentation tasks.
  • Pascal Voc 2012 and Cityscapes

    The dataset used in the paper is Pascal Voc 2012 and Cityscapes.