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 1221–1230 of 2262 papers

Title	Date	Tasks	Status
Active Testing: An Efficient and Robust Framework for Estimating Accuracy	Jul 2, 2018	Instance SegmentationMulti-Label Classification	—Unverified
Actor-Action Semantic Segmentation with Region Masks	Jul 23, 2018	Action SegmentationInstance Segmentation	—Unverified
AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts	Jan 1, 2023	Instance SegmentationMixture-of-Experts	—Unverified
Adapting Mask-RCNN for Automatic Nucleus Segmentation	May 1, 2018	Instance SegmentationObject	—Unverified
Adapting SAM for Volumetric X-Ray Data-sets of Arbitrary Sizes	Feb 9, 2024	Computed Tomography (CT)Instance Segmentation	—Unverified
Adapting Segment Anything Model for Unseen Object Instance Segmentation	Sep 23, 2024	DecoderInstance Segmentation	—Unverified
Adapting Vision Foundation Models for Plant Phenotyping	Oct 1, 2023	DecoderInstance Segmentation	—Unverified
Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation	Dec 7, 2020	Instance SegmentationPanoptic Segmentation	—Unverified
A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing	Dec 3, 2023	Autonomous NavigationData Augmentation	—Unverified
A Dataset for Lane Instance Segmentation in Urban Environments	Jul 3, 2018	Autonomous VehiclesInstance Segmentation	—Unverified

Show:10 25 50

← PrevPage 123 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	GLEE-Pro	mask AP	54.2	—	Unverified
9	ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)	mask AP	54.2	—	Unverified
10	SwinV2-G (HTC++)	mask AP	53.7	—	Unverified