-
EOLO: Embedded Object Segmentation only Look
Instance segmentation on embedded devices -
Semantic Segmentation with Deep Convolutional Nets and Fully Connected CRFs
The Pascal VOC dataset is a benchmark for object detection and instance segmentation. -
Pseudo-mask Augmented Object Detection
The proposed approach is validated using various state-of-the-art network architectures (VGG and ResNet) on several well-known object detection benchmarks (i.e., PASCAL VOC 2007... -
3D-RCNN: Instance-level 3D object reconstruction via render-and-compare
3D-RCNN: Instance-level 3D object reconstruction via render-and-compare. -
Microsoft COCO (MS-COCO) Dataset
A large-scale dataset for object detection and instance segmentation. -
PersonLab dataset
The PersonLab dataset is a benchmark for person pose estimation and instance segmentation. It contains 20,000 images with 80,000 annotated person instances. -
Stanford Large Scale 3D Indoor Spaces Dataset (S3DIS)
Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots. -
MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instan...
MosaicFusion: A simple yet effective diffusion-based data augmentation approach for large vocabulary instance segmentation. -
VFSS2022 dataset
The VFSS2022 dataset is a collection of 440 CT frames from Videofluoroscopic Swallowing Studies (VFSS) for instance segmentation in medical CT videos. -
OpenImages dataset V6
The OpenImages dataset V6 contains images with annotations for object detection and instance segmentation tasks. -
Dense RepPoints dataset
The dataset used in the paper is the Dense RepPoints dataset, which is a regression-based instance segmentation approach. -
Deep Affinity Net: Instance Segmentation via Affinity
Deep Affinity Net: an effective affinity-based approach accompanied with a new graph partitioning algorithm Cascade-GAEC. -
Conditional Convolutions for Instance Segmentation
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... -
BlendMask-RT
The dataset used in this paper for instance segmentation. -
KINS Dataset
A dataset for amodal instance segmentation, consisting of images with variable numbers of object instances. -
YouTube-VIS Dataset
The YouTube-VIS dataset is a large-scale dataset for instance segmentation, containing 2,883 videos and 131K instance masks. -
MOTS Dataset
The MOTS dataset is a variant of the MOT dataset, containing 4 training sequences and 4 test sequences. -
SOTR Dataset
The SOTR dataset is a custom dataset used for testing the proposed SOTR model.