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 776–800 of 2262 papers

Title	Date	Tasks	Status	Hype
SOLO: Segmenting Objects by Locations	Dec 10, 2019	ClusteringGeneral Classification	CodeCode Available	1
Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Picking	Dec 6, 2019	6D Pose Estimation using RGBInstance Segmentation	CodeCode Available	1
Weakly Supervised Cell Instance Segmentation by Propagating from Detection Response	Nov 29, 2019	Cell SegmentationCultural Vocal Bursts Intensity Prediction	CodeCode Available	1
CenterMask : Real-Time Anchor-Free Instance Segmentation	Nov 15, 2019	Instance SegmentationObject Detection	CodeCode Available	1
Classification Calibration for Long-tail Instance Segmentation	Oct 29, 2019	ClassificationGeneral Classification	CodeCode Available	1
SpatialFlow: Bridging All Tasks for Panoptic Segmentation	Oct 19, 2019	AllInstance Segmentation	CodeCode Available	1
PolarMask: Single Shot Instance Segmentation with Polar Representation	Sep 29, 2019	Distance regressionInstance Segmentation	CodeCode Available	1
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution	Sep 27, 2019	GPUInstance Segmentation	CodeCode Available	1
Global Aggregation then Local Distribution in Fully Convolutional Networks	Sep 16, 2019	Instance Segmentationobject-detection	CodeCode Available	1
Deep High-Resolution Representation Learning for Visual Recognition	Aug 20, 2019	Dichotomous Image SegmentationFace Alignment	CodeCode Available	1
Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature Fusion	Aug 10, 2019	Instance SegmentationNuclear Segmentation	CodeCode Available	1
LVIS: A Dataset for Large Vocabulary Instance Segmentation	Aug 8, 2019	Instance SegmentationObject	CodeCode Available	1
Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth	Jun 26, 2019	Autonomous DrivingClustering	CodeCode Available	1
MMDetection: Open MMLab Detection Toolbox and Benchmark	Jun 17, 2019	BenchmarkingInstance Segmentation	CodeCode Available	1
Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer	Jun 7, 2019	Action RecognitionGeneral Classification	CodeCode Available	1
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds	Jun 4, 2019	3D Instance SegmentationClustering	CodeCode Available	1
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities	May 30, 2019	DiversityInductive Bias	CodeCode Available	1
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images	May 30, 2019	Instance SegmentationObject	CodeCode Available	1
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations	Apr 10, 2019	image-classificationImage Classification	CodeCode Available	1
YOLACT: Real-time Instance Segmentation	Apr 4, 2019	GPUInstance Segmentation	CodeCode Available	1
Res2Net: A New Multi-scale Backbone Architecture	Apr 2, 2019	Image ClassificationInstance Segmentation	CodeCode Available	1
Deep High-Resolution Representation Learning for Human Pose Estimation	Feb 25, 2019	2D Human Pose Estimation2D Pose Estimation	CodeCode Available	1
Augmentation for small object detection	Feb 19, 2019	Instance SegmentationObject	CodeCode Available	1
Hybrid Task Cascade for Instance Segmentation	Jan 22, 2019	Instance Segmentationobject-detection	CodeCode Available	1
Slimmable Neural Networks	Dec 21, 2018	Instance SegmentationKeypoint Detection	CodeCode Available	1

Show:10 25 50

← PrevPage 32 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