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

Showing 401450 of 2262 papers

TitleStatusHype
Language-Assisted 3D Feature Learning for Semantic Scene UnderstandingCode1
Mean Shift Mask Transformer for Unseen Object Instance SegmentationCode1
PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item DetectionCode1
A Generalized Framework for Video Instance SegmentationCode1
Instance Segmentation for Chinese Character Stroke Extraction, Datasets and BenchmarksCode1
BARS: A Benchmark for Airport Runway SegmentationCode1
Large-batch Optimization for Dense Visual PredictionsCode1
Self-Supervised Learning via Maximum Entropy CodingCode1
Self-Supervised Learning with Masked Image Modeling for Teeth Numbering, Detection of Dental Restorations, and Instance Segmentation in Dental Panoramic RadiographsCode1
TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun DistillationCode1
A Tri-Layer Plugin to Improve Occluded DetectionCode1
Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel LogisticsCode1
TIVE: A Toolbox for Identifying Video Instance Segmentation ErrorsCode1
Hierarchical Approach for Joint Semantic, Plant Instance, and Leaf Instance Segmentation in the Agricultural DomainCode1
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object DetectionCode1
AISFormer: Amodal Instance Segmentation with TransformerCode1
Latency-aware Spatial-wise Dynamic NetworksCode1
Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance SegmentationCode1
BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance SegmentationCode1
4D Unsupervised Object DiscoveryCode1
OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point CloudsCode1
Instance Segmentation of Dense and Overlapping Objects via LayeringCode1
Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance SegmentationCode1
Effective Self-supervised Pre-training on Low-compute Networks without DistillationCode1
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-EncodersCode1
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision ModelsCode1
Learning Equivariant Segmentation with Instance-Unique QueryingCode1
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningCode1
Strong Instance Segmentation Pipeline for MMSports ChallengeCode1
Segmenting Known Objects and Unseen Unknowns without Prior KnowledgeCode1
MassMIND: Massachusetts Maritime INfrared DatasetCode1
MMV_Im2Im: An Open Source Microscopy Machine Vision Toolbox for Image-to-Image TransformationCode1
Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and BeyondCode1
Refine and Represent: Region-to-Object Representation LearningCode1
Applying Eigencontours to PolarMask-Based Instance SegmentationCode1
InstanceFormer: An Online Video Instance Segmentation FrameworkCode1
Open-Vocabulary Universal Image Segmentation with MaskCLIPCode1
Unifying Visual Perception by Dispersible Points LearningCode1
DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality AnnotationsCode1
Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance SegmentationCode1
Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance SegmentationCode1
Instance As Identity: A Generic Online Paradigm for Video Instance SegmentationCode1
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
Visual Recognition by RequestCode1
Video Mask Transfiner for High-Quality Video Instance SegmentationCode1
Compositional Human-Scene Interaction Synthesis with Semantic ControlCode1
Active Pointly-Supervised Instance SegmentationCode1
DeVIS: Making Deformable Transformers Work for Video Instance SegmentationCode1
Long-tailed Instance Segmentation using Gumbel Optimized LossCode1
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise BinarizationCode1
Show:102550
← PrevPage 9 of 46Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-HAP5080.8Unverified
2ResNeSt-200 (multi-scale)AP5070.2Unverified
3CenterMask + VoVNetV2-99 (multi-scale)AP5066.2Unverified
4CenterMask + VoVNetV2-57 (single-scale)AP5060.8Unverified
5Co-DETRmask AP57.1Unverified
6CBNetV2 (EVA02, single-scale)mask AP56.1Unverified
7ISDA (ResNet-50)APL55.7Unverified
8EVAmask AP55.5Unverified
9FD-SwinV2-Gmask AP55.4Unverified
10Mask Frozen-DETRmask AP55.3Unverified
#ModelMetricClaimedVerifiedStatus
1InternImage-BGFLOPs501Unverified
2Co-DETRmask AP56.6Unverified
3ViT-CoMer-L (Mask RCNN, DINOv2)mask AP55.9Unverified
4InternImage-Hmask AP55.4Unverified
5EVAmask AP55Unverified
6Mask Frozen-DETRmask AP54.9Unverified
7MasK DINO (SwinL, multi-scale)mask AP54.5Unverified
8ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2Unverified
9GLEE-Promask AP54.2Unverified
10SwinV2-G (HTC++)mask AP53.7Unverified