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 826–850 of 2262 papers

Title	Date	Tasks	Status	Hype
Hi4D: 4D Instance Segmentation of Close Human Interaction	Mar 27, 2023	Instance SegmentationSemantic Segmentation	CodeCode Available	1
You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding	Mar 26, 2023	3D Instance SegmentationInstance Segmentation	CodeCode Available	1
BoxVIS: Video Instance Segmentation with Box Annotations	Mar 26, 2023	Instance SegmentationSemantic Segmentation	CodeCode Available	1
UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes	Mar 25, 2023	3D Instance SegmentationInstance Segmentation	—Unverified	0
MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos	Mar 25, 2023	Instance SegmentationSemantic Segmentation	CodeCode Available	1
SUDS: Scalable Urban Dynamic Scenes	Mar 25, 2023	3D Instance SegmentationInstance Segmentation	—Unverified	0
DoNet: Deep De-overlapping Network for Cytology Instance Segmentation	Mar 25, 2023	Instance SegmentationRegion Proposal	CodeCode Available	1
A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation	Mar 23, 2023	image-classificationImage Classification	—Unverified	0
Position-Guided Point Cloud Panoptic Segmentation Transformer	Mar 23, 2023	Instance SegmentationPanoptic Segmentation	CodeCode Available	1
Uncertainty Aware Active Learning for Reconfiguration of Pre-trained Deep Object-Detection Networks for New Target Domains	Mar 22, 2023	Active LearningInformativeness	—Unverified	0
On Domain-Specific Pre-Training for Effective Semantic Perception in Agricultural Robotics	Mar 22, 2023	Data AugmentationInstance Segmentation	—Unverified	0
Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images	Mar 21, 2023	Active LearningDiversity	—Unverified	0
BoxSnake: Polygonal Instance Segmentation with Box Supervision	Mar 21, 2023	Box-supervised Instance SegmentationInstance Segmentation	CodeCode Available	1
3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers	Mar 21, 2023	DecoderInstance Segmentation	CodeCode Available	1
Weakly-Supervised Text Instance Segmentation	Mar 20, 2023	Contrastive LearningInstance Segmentation	—Unverified	0
Bimodal SegNet: Instance Segmentation Fusing Events and RGB Frames for Robotic Grasping	Mar 20, 2023	DecoderInstance Segmentation	CodeCode Available	0
Making Vision Transformers Efficient from A Token Sparsification View	Mar 15, 2023	Efficient ViTsimage-classification	CodeCode Available	1
FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation	Mar 15, 2023	DecoderInstance Segmentation	CodeCode Available	2
Panoptic One-Click Segmentation: Applied to Agricultural Data	Mar 15, 2023	Instance SegmentationSegmentation	—Unverified	0
SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentation	Mar 14, 2023	Box-supervised Instance SegmentationInstance Segmentation	CodeCode Available	1
A Simple Framework for Open-Vocabulary Segmentation and Detection	Mar 14, 2023	Instance SegmentationPanoptic Segmentation	CodeCode Available	3
DynaMask: Dynamic Mask Selection for Instance Segmentation	Mar 14, 2023	Instance SegmentationSegmentation	CodeCode Available	1
CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention	Mar 13, 2023	image-classificationImage Classification	CodeCode Available	2
Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning	Mar 13, 2023	Instance Segmentationobject-detection	CodeCode Available	1
OSIS: Efficient One-stage Network for 3D Instance Segmentation	Mar 13, 2023	3D Instance SegmentationClustering	—Unverified	0

Show:10 25 50

← PrevPage 34 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