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 1651–1700 of 2262 papers

TitleStatusHype
Classifying Breast Histopathology Images with a Ductal Instance-Oriented PipelineCode1
Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions—0
The Lottery Ticket Hypothesis for Object RecognitionCode1
CARAFE++: Unified Content-Aware ReAssembly of FEatures—0
Learning Video Instance Segmentation with Recurrent Graph Neural Networks—0
Rethinking Learnable Tree Filter for Generic Feature TransformCode1
Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation—0
The Role of Regularization in Shaping Weight and Node Pruning Dependency and Dynamics—0
CompFeat: Comprehensive Feature Aggregation for Video Instance SegmentationCode1
PeR-ViS: Person Retrieval in Video Surveillance using Semantic DescriptionCode1
BoxInst: High-Performance Instance Segmentation with Box Annotations—0
Robust Instance Segmentation through Reasoning about Multi-Object OcclusionCode1
Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline—0
Single-shot Path Integrated Panoptic Segmentation—0
Towards Part-Based Understanding of RGB-D ScansCode1
Learning Universal Shape Dictionary for Realtime Instance SegmentationCode1
Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation—0
Single-Shot Lightweight Model For The Detection of Lesions And The Prediction of COVID-19 From Chest CT ScansCode0
End-to-End Video Instance Segmentation with TransformersCode1
Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction—0
The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation—0
MultiStar: Instance Segmentation of Overlapping Objects with Star-Convex PolygonsCode1
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic ConvolutionCode1
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation—0
CellSegmenter: unsupervised representation learning and instance segmentation of modular images—0
Prior to Segment: Foreground Cues for Weakly Annotated Classes in Partially Supervised Instance SegmentationCode1
Scaling Wide Residual Networks for Panoptic Segmentation—0
3D Registration for Self-Occluded Objects in Context—0
One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection TasksCode1
Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized ProteinsCode0
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance SegmentationCode1
Unifying Instance and Panoptic Segmentation with Dynamic Rank-1 Convolutions—0
Attention-Based Transformers for Instance Segmentation of Cells in MicrostructuresCode1
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
SeekNet: Improved Human Instance Segmentation and Tracking via Reinforcement Learning Based Optimized Robot Relocation—0
Towards Efficient Scene Understanding via Squeeze ReasoningCode1
Lightweight Model For The Prediction of COVID-19 Through The Detection And Segmentation of Lesions in Chest CT ScansCode1
Learning Regional Purity for Instance Segmentation on 3D Point CloudsCode0
ASIST: Annotation-free synthetic instance segmentation and tracking for microscope video analysis—0
Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic SegmentationCode1
Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds—0
Perception for Autonomous Systems (PAZ)Code1
Instance Semantic Segmentation Benefits from Generative Adversarial NetworksCode1
Detection and Segmentation of Lesion Areas in Chest CT Scans For The Prediction of COVID-19Code1
Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian ModelCode1
2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020—0
AutoBSS: An Efficient Algorithm for Block Stacking Style Search—0
TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power LinesCode1
Multi-Stage Fusion for One-Click Segmentation—0
Localized Interactive Instance Segmentation—0
Show:102550
← PrevPage 34 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