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 501–525 of 2262 papers

Title	Date	Tasks	Status	Hype
D2Det: Towards High Quality Object Detection and Instance Segmentation	Jun 1, 2020	Instance SegmentationObject	CodeCode Available	1
GradAug: A New Regularization Method for Deep Neural Networks	Jun 14, 2020	Instance Segmentationobject-detection	CodeCode Available	1
AISFormer: Amodal Instance Segmentation with Transformer	Oct 12, 2022	Amodal Instance SegmentationDecoder	CodeCode Available	1
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision	May 13, 2021	Box-supervised Instance SegmentationInstance Segmentation	CodeCode Available	1
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement	Sep 20, 2021	Image-level Supervised Instance SegmentationInstance Segmentation	CodeCode Available	1
Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation	Mar 27, 2021	ClusteringInstance Segmentation	CodeCode Available	1
Exploring Classification Equilibrium in Long-Tailed Object Detection	Aug 17, 2021	Classificationimbalanced classification	CodeCode Available	1
Panoptic Vision-Language Feature Fields	Sep 11, 2023	Contrastive LearningInstance Segmentation	CodeCode Available	1
PartDistillation: Learning Parts From Instance Segmentation	Jan 1, 2023	Instance SegmentationObject	CodeCode Available	1
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning	Oct 3, 2022	ClusteringDepth Estimation	CodeCode Available	1
Evolving Normalization-Activation Layers	Apr 6, 2020	image-classificationImage Classification	CodeCode Available	1
Explain Any Concept: Segment Anything Meets Concept-Based Explanation	May 17, 2023	Instance SegmentationSemantic Segmentation	CodeCode Available	1
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts	Dec 16, 2020	3D Semantic SegmentationInstance Segmentation	CodeCode Available	1
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection	Dec 15, 2020	Instance SegmentationLong-tailed Object Detection	CodeCode Available	1
Amodal Intra-class Instance Segmentation: Synthetic Datasets and Benchmark	Mar 12, 2023	Amodal Instance SegmentationInstance Segmentation	CodeCode Available	1
Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentation	Sep 4, 2024	Dichotomous Image SegmentationImage Segmentation	CodeCode Available	1
Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation	Jan 2, 2023	Caption GenerationInstance Segmentation	CodeCode Available	1
3D Instances as 1D Kernels	Jul 15, 2022	3D Instance SegmentationInstance Segmentation	CodeCode Available	1
EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion	Mar 23, 2020	GPUInstance Segmentation	CodeCode Available	1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention	Oct 10, 2023	Computational Efficiencyimage-classification	CodeCode Available	1
End-to-End Semi-Supervised Object Detection with Soft Teacher	Jun 16, 2021	Instance Segmentationobject-detection	CodeCode Available	1
End-to-End Referring Video Object Segmentation with Multimodal Transformers	Nov 29, 2021	Inductive BiasInstance Segmentation	CodeCode Available	1
End-to-End Video Instance Segmentation with Transformers	Nov 30, 2020	Instance SegmentationSegmentation	CodeCode Available	1
Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment	Aug 6, 2024	Instance SegmentationSegmentation	CodeCode Available	1
Benchmarking Self-Supervised Learning on Diverse Pathology Datasets	Dec 9, 2022	BenchmarkingClassification	CodeCode Available	1

Show:10 25 50

← PrevPage 21 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	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