Instance Segmentation

Instance Segmentation is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.

Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 2176–2200 of 2262 papers

Title	Date	Tasks	Status	Hype
Weakly Supervised Instance Segmentation using Class Peak Response	Apr 3, 2018	General ClassificationImage-level Supervised Instance Segmentation	CodeCode Available	0
Predicting Future Instance Segmentation by Forecasting Convolutional Features	Mar 30, 2018	Instance SegmentationOptical Flow Estimation	CodeCode Available	0
Pose2Seg: Detection Free Human Instance Segmentation	Mar 28, 2018	2D Human Pose EstimationHuman Instance Segmentation	CodeCode Available	0
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model	Mar 22, 2018	Instance SegmentationKeypoint Detection	CodeCode Available	0
Learning to Cluster for Proposal-Free Instance Segmentation	Mar 17, 2018	Autonomous DrivingClustering	CodeCode Available	0
Learning to Segment via Cut-and-Paste	Mar 16, 2018	Instance SegmentationObject	CodeCode Available	0
Learning deep structured active contours end-to-end	Mar 16, 2018	Instance SegmentationSegmentation	CodeCode Available	0
The ApolloScape Open Dataset for Autonomous Driving and its Application	Mar 16, 2018	Autonomous DrivingInstance Segmentation	CodeCode Available	1
Pseudo Mask Augmented Object Detection	Mar 15, 2018	Instance SegmentationObject	—Unverified	0
Path Aggregation Network for Instance Segmentation	Mar 5, 2018	Instance Segmentationobject-detection	CodeCode Available	1
IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network	Feb 28, 2018	Instance SegmentationSemantic Segmentation	CodeCode Available	0
Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image	Feb 28, 2018	BenchmarkingInstance Segmentation	—Unverified	0
Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells	Feb 21, 2018	Instance SegmentationSemantic Segmentation	CodeCode Available	1
Towards End-to-End Lane Detection: an Instance Segmentation Approach	Feb 15, 2018	Instance SegmentationLane Detection	CodeCode Available	0
Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters	Feb 1, 2018	Instance SegmentationOne-Shot Learning	—Unverified	0
SRDA: Generating Instance Segmentation Annotation Via Scanning, Reasoning And Domain Adaptation	Jan 26, 2018	Domain AdaptationInstance Segmentation	CodeCode Available	0
Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network	Jan 4, 2018	Instance SegmentationObject	—Unverified	0
PixelLink: Detecting Scene Text via Instance Segmentation	Jan 4, 2018	Instance Segmentationregression	CodeCode Available	0
Panoptic Segmentation	Jan 3, 2018	Image SegmentationInstance Segmentation	CodeCode Available	1
Brain Tumor Segmentation Based on Refined Fully Convolutional Neural Networks with A Hierarchical Dice Loss	Dec 25, 2017	Binary ClassificationBrain Tumor Segmentation	CodeCode Available	0
The ParallelEye Dataset: Constructing Large-Scale Artificial Scenes for Traffic Vision Research	Dec 22, 2017	Instance SegmentationObject Tracking	—Unverified	0
Recurrent Pixel Embedding for Instance Grouping	Dec 22, 2017	Boundary DetectionClustering	CodeCode Available	0
MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features	Dec 13, 2017	Instance SegmentationObject	—Unverified	0
iPose: Instance-Aware 6D Pose Estimation of Partly Occluded Objects	Dec 5, 2017	6D Pose Estimation6D Pose Estimation using RGB	—Unverified	0
Recurrent Neural Networks for Semantic Instance Segmentation	Dec 2, 2017	Instance SegmentationObject	CodeCode Available	0

Show:10 25 50

← PrevPage 88 of 91Next →

All datasets COCO test-dev COCO minival LVIS v1.0 val Cityscapes val ADE20K val ARMBench Occluded COCO OoDIS Separated COCO TBBR BDD100K val COCO val (panoptic labels)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	InternImage-H	AP50	80.8	—	Unverified
2	ResNeSt-200 (multi-scale)	AP50	70.2	—	Unverified
3	CenterMask + VoVNetV2-99 (multi-scale)	AP50	66.2	—	Unverified
4	CenterMask + VoVNetV2-57 (single-scale)	AP50	60.8	—	Unverified
5	Co-DETR	mask AP	57.1	—	Unverified
6	CBNetV2 (EVA02, single-scale)	mask AP	56.1	—	Unverified
7	ISDA (ResNet-50)	APL	55.7	—	Unverified
8	EVA	mask AP	55.5	—	Unverified
9	FD-SwinV2-G	mask AP	55.4	—	Unverified
10	Mask Frozen-DETR	mask AP	55.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	InternImage-B	GFLOPs	501	—	Unverified
2	Co-DETR	mask AP	56.6	—	Unverified
3	ViT-CoMer-L (Mask RCNN, DINOv2)	mask AP	55.9	—	Unverified
4	InternImage-H	mask AP	55.4	—	Unverified
5	EVA	mask AP	55	—	Unverified
6	Mask Frozen-DETR	mask AP	54.9	—	Unverified
7	MasK DINO (SwinL, multi-scale)	mask AP	54.5	—	Unverified
8	ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)	mask AP	54.2	—	Unverified
9	GLEE-Pro	mask AP	54.2	—	Unverified
10	SwinV2-G (HTC++)	mask AP	53.7	—	Unverified