SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 601–650 of 2262 papers

TitleStatusHype
GRIT: General Robust Image Task BenchmarkCode1
Large-batch Optimization for Dense Visual PredictionsCode1
Graph Relation Distillation for Efficient Biomedical Instance SegmentationCode1
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionCode1
LeafMask: Towards Greater Accuracy on Leaf SegmentationCode1
Learn Fast, Segment Well: Fast Object Segmentation Learning on the iCub RobotCode1
ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR DataCode1
Distilling Knowledge via Knowledge ReviewCode1
GradAug: A New Regularization Method for Deep Neural NetworksCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Learning Object Bounding Boxes for 3D Instance Segmentation on Point CloudsCode1
PaCa-ViT: Learning Patch-to-Cluster Attention in Vision TransformersCode1
Deep Learning based Food Instance Segmentation using Synthetic DataCode1
Learning Saliency Propagation for Semi-Supervised Instance SegmentationCode1
Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning DynamicsCode1
Global Aggregation then Local Distribution in Fully Convolutional NetworksCode1
Boundary-assisted Region Proposal Networks for Nucleus SegmentationCode1
A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection from Aerial ImagesCode1
DocSegTr: An Instance-Level End-to-End Document Image Segmentation TransformerCode1
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group PropagationCode1
An Instance Segmentation Dataset of Yeast Cells in MicrostructuresCode1
LESS: Label-Efficient and Single-Stage Referring 3D SegmentationCode1
Boundary-preserving Mask R-CNNCode1
DoNet: Deep De-overlapping Network for Cytology Instance SegmentationCode1
BoundarySqueeze: Image Segmentation as Boundary SqueezingCode1
Lightweight Model For The Prediction of COVID-19 Through The Detection And Segmentation of Lesions in Chest CT ScansCode1
ELSA: Enhanced Local Self-Attention for Vision TransformerCode1
Learning Dynamic Query Combinations for Transformer-based Object Detection and SegmentationCode1
Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context TermsCode1
Location-Sensitive Visual Recognition with Cross-IOU LossCode1
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point CloudCode1
Deep learning approaches to building rooftop thermal bridge detection from aerial imagesCode1
Test-time Adaptation with Slot-Centric ModelsCode1
DropLoss for Long-Tail Instance SegmentationCode1
BoxeR: Box-Attention for 2D and 3D TransformersCode1
Embedding-based Instance Segmentation in MicroscopyCode1
Low Latency Instance Segmentation by Continuous Clustering for LiDAR SensorsCode1
DVIS: Decoupled Video Instance Segmentation FrameworkCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic ConvolutionCode1
DynaMask: Dynamic Mask Selection for Instance SegmentationCode1
Dynamic Convolution for 3D Point Cloud Instance SegmentationCode1
BoxSnake: Polygonal Instance Segmentation with Box SupervisionCode1
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object DetectionCode1
BARS: A Benchmark for Airport Runway SegmentationCode1
Instance Semantic Segmentation Benefits from Generative Adversarial NetworksCode1
Effective Self-supervised Pre-training on Low-compute Networks without DistillationCode1
BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance SegmentationCode1
GAInS: Gradient Anomaly-aware Biomedical Instance SegmentationCode1
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo LabelersCode1
Show:102550
← PrevPage 13 of 46Next →
All datasetsCOCO test-devCOCO minivalLVIS v1.0 valCityscapes valADE20K valARMBenchOccluded COCOOoDISSeparated COCOTBBRBDD100K valCOCO val (panoptic labels)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-HAP5080.8—Unverified
2ResNeSt-200 (multi-scale)AP5070.2—Unverified
3CenterMask + VoVNetV2-99 (multi-scale)AP5066.2—Unverified
4CenterMask + VoVNetV2-57 (single-scale)AP5060.8—Unverified
5Co-DETRmask AP57.1—Unverified
6CBNetV2 (EVA02, single-scale)mask AP56.1—Unverified
7ISDA (ResNet-50)APL55.7—Unverified
8EVAmask AP55.5—Unverified
9FD-SwinV2-Gmask AP55.4—Unverified
10Mask Frozen-DETRmask AP55.3—Unverified
#ModelMetricClaimedVerifiedStatus
1InternImage-BGFLOPs501—Unverified
2Co-DETRmask AP56.6—Unverified
3ViT-CoMer-L (Mask RCNN, DINOv2)mask AP55.9—Unverified
4InternImage-Hmask AP55.4—Unverified
5EVAmask AP55—Unverified
6Mask Frozen-DETRmask AP54.9—Unverified
7MasK DINO (SwinL, multi-scale)mask AP54.5—Unverified
8ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2—Unverified
9GLEE-Promask AP54.2—Unverified
10SwinV2-G (HTC++)mask AP53.7—Unverified