-
Tiny Anomalies
A novel benchmark for evaluating methods on the original, high-resolution image and ground-truth masks, focusing on segmentation performance as a function of the size of anomalies. -
Fission Gas Bubble Segmentation on U-10Zr Annular Fuels
The dataset is used for fission gas bubble segmentation on U-10Zr annular fuels. -
MICCAI 2018 segmentation decathlon challenge
MRI dataset for hippocampus segmentation -
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... -
Middlebury dataset
Guided depth super-resolution (GDSR) involves restor- ing missing depth details using the high-resolution RGB image of the same scene. -
Penobscot 3D Survey
The Penobscot 3D Survey dataset is a real seismic dataset acquired offshore Nova Scotia, Canada. It consists of a horizontal stack of 2D seismic images (slices), creating a 3D... -
Graphic Narrative Corpus
The Graphic Narrative Corpus (GNC) is a dataset of annotated comic book pages, representing English-language graphic novels with a variety of styles. -
Persian Rice Classification and Segmentation Dataset
The dataset comprises various rice types photographed under natural conditions without professional lighting or equipment, presenting a challenging yet practical classification... -
MIT Scene Parsing Dataset
The MIT scene parsing dataset used for training the FCN network. -
Fully Convolutional Networks for Automatically Generating Image Masks to Trai...
The proposed method for automatically generating image masks to train Mask R-CNN for object detection. -
GWHD dataset
A large-scale computationally annotated dataset of image-mask pairs and a large dataset of unannotated images extracted from video frames. -
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segme...
The V-Net is a deep learning model for medical image segmentation that uses a U-Net architecture. -
Microsoft COCO Dataset
The MS COCO 2014 Dataset contains images of 91 object categories, which contains 82783 training images, 40504 validation images and 40775 testing images. -
ICNet for Real-Time Semantic Segmentation
Real-time semantic segmentation system for high-resolution images -
COCO panoptic validation set
Panoptic segmentation aims to unify instance and semantic segmentation in the same framework. Existing works propose to merge instance and semantic segmentation using... -
COCO panoptic segmentation
Panoptic segmentation aims to unify instance and semantic segmentation in the same framework. Existing works propose to merge instance and semantic segmentation using... -
CamVid Dataset
CamVid dataset is a benchmark dataset for semantic segmentation. It consists of 700 images with 11 object classes. -
BDD100K Dataset
BDD100K Dataset is a large-scale dataset for autonomous driving, containing 100,000 images, with 20,000 images for training and 80,000 images for testing. -
Bloodstain Analysis AI Tool
Bloodstain pattern analysis dataset for bloodstain image segmentation
