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 1801–1810 of 2262 papers

Title	Date	Tasks	Status
How Shift Equivariance Impacts Metric Learning for Instance Segmentation	Jan 14, 2021	DecoderInstance Segmentation	CodeCode Available
One Shot Model For The Prediction of COVID-19 and Lesions Segmentation In Chest CT Scans Through The Affinity Among Lesion Mask Features	Jan 4, 2021	COVID-19 DiagnosisInstance Segmentation	CodeCode Available
Weakly Supervised Multi-Object Tracking and Segmentation	Jan 3, 2021	Instance SegmentationMulti-Object Tracking	—Unverified
ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations	Jan 3, 2021	Instance SegmentationSegmentation	—Unverified
Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation	Jan 1, 2021	Instance Segmentationobject-detection	—Unverified
Aggregation With Feature Detection	Jan 1, 2021	Instance Segmentationobject-detection	—Unverified
Poly-NL: Linear Complexity Non-Local Layers With 3rd Order Polynomials	Jan 1, 2021	Face DetectionInstance Segmentation	—Unverified
Contextual Graph Reasoning Networks	Jan 1, 2021	2D Human Pose EstimationInstance Segmentation	—Unverified
EMPIRICAL UPPER BOUND IN OBJECT DETECTION	Jan 1, 2021	Instance SegmentationObject	—Unverified
Learning a unified label space	Jan 1, 2021	Instance SegmentationObject	—Unverified

Show:10 25 50

← PrevPage 181 of 227Next →

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