154 datasets found

Private OCT dataset used for testing

Open-access OCT dataset used for segmentation pre-training

Open-access OCT datasets used for pre-training and fine-tuning the model

The 2021 Multimodal Brain Tumor Segmentation Challenge (BraTS21) dataset

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,...

The dataset used for image classification and semantic image segmentation.

The dataset is used for histopathological image segmentation. It contains H&E stained histopathological images along with annotations.

Skin lesion segmentation dataset for PH2

Ref-Youtube-VOS is an extensive referring video object segmentation dataset that comprises approximately 15,000 referring expressions associated with more than 3,900 videos.

LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the de facto method is to project a 3D point cloud to get...

A dataset for segment anything model (SAM) to evaluate its performance.

Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: segment anything (SegAny), which utilizes a certain point to predict the mask for a...

The VSPW dataset is a large-scale dataset for video scene parsing in the wild, containing 2,806 videos with 480x853 pixel frames and 124 semantic categories.

The BRATS 2018, 2019 and 2020 datasets are used for training and evaluation of the proposed 3D UNet model for brain tumor segmentation.

The Total Segmentator dataset contains 1204 CT images with labels of 104 anatomical structures.

The dataset is a collection of 3D multi-modality MRI spine images for intervertebral disc localization and segmentation.

The dataset used for testing the U-net architecture for automatic segmentation of LGE-MRI images.

The dataset used for training and testing the U-net architecture for automatic segmentation of LGE-MRI images.

Skin cancer segmentation using Segment Anything Model

The EO-1 Hyperion dataset consists of 35 HS images gathered from NASA’s Earth Observing-1 (EO-1) mission.