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 2226–2250 of 2262 papers

Title	Date	Tasks	Status
Deep GrabCut for Object Selection	Jul 2, 2017	DecoderInstance Segmentation	—Unverified
Indoor Scene Parsing With Instance Segmentation, Semantic Labeling and Support Relationship Inference	Jul 1, 2017	Instance SegmentationScene Parsing	—Unverified
Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects	Jun 20, 2017	Instance SegmentationObject	CodeCode Available
BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks	Jun 7, 2017	Bayesian InferenceInstance Segmentation	—Unverified
Towards Instance Segmentation with Object Priority: Prominent Object Detection and Recognition	Apr 24, 2017	Instance SegmentationObject	—Unverified
Instance-Level Salient Object Segmentation	Apr 12, 2017	Instance SegmentationObject	—Unverified
Pixelwise Instance Segmentation with a Dynamically Instantiated Network	Apr 7, 2017	Instance SegmentationObject	CodeCode Available
Pose2Instance: Harnessing Keypoints for Person Instance Segmentation	Apr 4, 2017	Instance SegmentationSegmentation	—Unverified
Bootstrapping Labelled Dataset Construction for Cow Tracking and Behavior Analysis	Mar 30, 2017	Instance SegmentationObject	—Unverified
Semantic Instance Segmentation via Deep Metric Learning	Mar 30, 2017	Instance SegmentationMetric Learning	CodeCode Available
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth	Dec 15, 2016	3D ReconstructionCamera Pose Estimation	CodeCode Available
Boundary-aware Instance Segmentation	Dec 9, 2016	Instance SegmentationObject	—Unverified
Learning Video Object Segmentation from Static Images	Dec 8, 2016	Instance SegmentationObject	CodeCode Available
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing	Dec 8, 2016	Instance SegmentationSemantic Segmentation	—Unverified
Efficient Pose and Cell Segmentation using Column Generation	Dec 1, 2016	Cell SegmentationEfficient Exploration	—Unverified
TorontoCity: Seeing the World with a Million Eyes	Dec 1, 2016	Instance SegmentationSemantic Segmentation	—Unverified
Object Detection Free Instance Segmentation With Labeling Transformations	Nov 28, 2016	Instance SegmentationObject	—Unverified
Deep Watershed Transform for Instance Segmentation	Nov 24, 2016	Instance SegmentationObject	CodeCode Available
Gland Instance Segmentation Using Deep Multichannel Neural Networks	Nov 21, 2016	Instance SegmentationSegmentation	—Unverified
Associative Embedding: End-to-End Learning for Joint Detection and Grouping	Nov 16, 2016	2D Human Pose EstimationInstance Segmentation	CodeCode Available
Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data	Nov 9, 2016	Instance SegmentationScene Text Recognition	—Unverified
Bottom-up Instance Segmentation using Deep Higher-Order CRFs	Sep 8, 2016	Instance SegmentationObject	—Unverified
Gland Instance Segmentation by Deep Multichannel Neural Networks	Jul 17, 2016	Instance SegmentationSegmentation	—Unverified
Gland Instance Segmentation by Deep Multichannel Side Supervision	Jul 12, 2016	Instance SegmentationSegmentation	—Unverified
End-to-End Instance Segmentation with Recurrent Attention	May 30, 2016	Autonomous DrivingImage Captioning	CodeCode Available

Show:10 25 50

← PrevPage 90 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