52 datasets found

A large-scale dataset for object detection and instance segmentation.

Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots.

Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots.

MosaicFusion: A simple yet effective diffusion-based data augmentation approach for large vocabulary instance segmentation.

The AVA instance segmentation challenge dataset, which contains difficult accessibility-related object categories such as ’wheelchair’ and ’cane’ set in a synthetic dataset...

The dataset used in the paper is the Dense RepPoints dataset, which is a regression-based instance segmentation approach.

Deep Affinity Net: an effective affinity-based approach accompanied with a new graph partitioning algorithm Cascade-GAEC.

A large-scale carton dataset for detection and segmentation, containing 250,000 instance masks from 16,136 images.

Instance segmentation is a fundamental yet challenging task in computer vision, which requires an algorithm to predict a per-pixel mask with a category label for each instance...

The dataset used in this paper for instance segmentation.

A dataset for amodal instance segmentation, consisting of images with variable numbers of object instances.

The YouTube-VIS dataset is a large-scale dataset for instance segmentation, containing 2,883 videos and 131K instance masks.

The MOTS dataset is a variant of the MOT dataset, containing 4 training sequences and 4 test sequences.

The SOTR dataset is a custom dataset used for testing the proposed SOTR model.

iSAID dataset is a large-scale high-resolution remote sensing dataset for aerial instance segmentation, containing many small objects with complex backgrounds.

The internal dataset contains 6 million real-world driving scenarios from Las Vegas (LV), Seattle (SEA), San Francisco (SF), and the campus of the Stanford Linear Accelerator...

A dataset for training instance segmentation networks for hair wisp extraction.

A hair wisp dataset for instance segmentation, consisting of real portrait photos and ground-truth annotations of hair wisps.

SA-1B is a large-scale benchmark for instance segmentation and object detection.

LVIS is a large-scale benchmark for instance segmentation and object detection.