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 801825 of 2262 papers

TitleStatusHype
HCFormer: Unified Image Segmentation with Hierarchical ClusteringCode1
FsaNet: Frequency Self-attention for Semantic SegmentationCode1
Clustering Plotted Data by Image SegmentationCode1
Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity FusionCode1
Fully Automated Scan-to-BIM Via Point Cloud Instance SegmentationCode1
Res2Net: A New Multi-scale Backbone ArchitectureCode1
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid NetworkCode1
ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity TrackingCode1
GAInS: Gradient Anomaly-aware Biomedical Instance SegmentationCode1
Instance Semantic Segmentation Benefits from Generative Adversarial NetworksCode1
Segmentation and Tracking of Vegetable Plants by Exploiting Vegetable Shape Feature for Precision Spray of Agricultural RobotsCode1
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo LabelersCode1
OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language ModelCode1
SOIT: Segmenting Objects with Instance-Aware TransformersCode1
TransMix: Attend to Mix for Vision TransformersCode1
Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise AffinityCode1
DARCNN: Domain Adaptive Region-based Convolutional Neural Network forUnsupervised Instance Segmentation in Biomedical ImagesCode0
DARCNN: Domain Adaptive Region-based Convolutional Neural Network for Unsupervised Instance Segmentation in Biomedical ImagesCode0
Recursively Refined R-CNN: Instance Segmentation with Self-RoI RebalancingCode0
DAN-NucNet: A dual attention based framework for nuclei segmentation in cancer histology images under wild clinical conditionsCode0
Recurrent Pixel Embedding for Instance GroupingCode0
A Benchmark of Long-tailed Instance Segmentation with Noisy LabelsCode0
Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized ProteinsCode0
CyclePose -- Leveraging Cycle-Consistency for Annotation-Free Nuclei Segmentation in Fluorescence MicroscopyCode0
Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data GenerationCode0
Show:102550
← PrevPage 33 of 91Next →

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