-
Automatic Building Extraction in Aerial Scenes
Aerial images and building footprints from GIS resources -
Psoas muscle segmentation dataset
The dataset used in this paper for psoas muscle segmentation in low-dose X-ray computed tomography images. -
SemSegLoss
A python package consisting of some well-known loss functions widely used for image segmentation. -
LoveDA dataset
The LoveDA dataset consists of 5,987 high-quality optical remote sensing images with a resolution of 0.3 meters per pixel. -
Underwater Change Detection dataset
The Underwater Change Detection dataset contains images of underwater scenes. -
Image Segmentation
The Image Segmentation dataset is used to evaluate the performance of the ensemble average rule. -
Deep Automatic Portrait Matting
The dataset used for training and testing the proposed LSSC system, which consists of 1530 training images and 170 test images in RGB format. -
Video Segmentation Datasets
The dataset used for video segmentation, including Moving MNIST, Change detection, Segtrack V2, and Davis datasets. -
Vaihingen dataset
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)... -
SegDiff: Image Segmentation with Diffusion Probabilistic Models
Diffusion Probabilistic Models are employed for state-of-the-art image generation. In this work, we present a method for extending such models for performing image segmentation. -
TGS Salt Identification Challenge
The dataset used for this project contains 4,000 seismic images with 4,000 labeled mask images. The seismic images are in grayscale, and the mask images are in black and white. -
Pascal VOC Challenge
The Pascal VOC Challenge dataset is a benchmark for object detection and image segmentation. -
CATCH dataset
The CATCH dataset is used to test the proposed Style-Extracting Diffusion Models (STEDM) for canine cancer histology image segmentation. -
HER2 dataset
The HER2 dataset is used to test the proposed Style-Extracting Diffusion Models (STEDM) for histopathology image segmentation. -
MIT-Adobe FiveK
The MIT-Adobe FiveK dataset, a large-scale dataset for image segmentation and object detection.
