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 1201–1250 of 2262 papers

TitleStatusHype
Uni3DL: Unified Model for 3D and Language Understanding—0
A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors—0
A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing—0
CellMixer: Annotation-free Semantic Cell Segmentation of Heterogeneous Cell Populations—0
Union-over-Intersections: Object Detection beyond Winner-Takes-AllCode0
Quantification of cardiac capillarization in single-immunostained myocardial slices using weakly supervised instance segmentation—0
Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework—0
Multi-task Planar Reconstruction with Feature Warping GuidanceCode0
ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation—0
Text and Click inputs for unambiguous open vocabulary instance segmentationCode0
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation—0
Deep learning-based instance segmentation for the precise automated quantification of digital breast cancer immunohistochemistry images—0
GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding—0
Self-trained Panoptic Segmentation—0
ToSkA: Topological Skeleton Analysis for Network-Based Shape Representation and Evaluation of Objects from Cells to Death Stars—0
VertDetect: Fully End-to-End 3D Vertebral Instance Segmentation Model—0
PWISeg: Point-based Weakly-supervised Instance Segmentation for Surgical InstrumentsCode0
3DFusion, A real-time 3D object reconstruction pipeline based on streamed instance segmented data—0
SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification—0
SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Store—0
SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis—0
Zero-Shot Enhancement of Low-Light Image Based on Retinex DecompositionCode0
An Empirical Study of Uncertainty in Polygon Annotation and the Impact of Quality Assurance—0
ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification—0
Scattering Vision Transformer: Spectral Mixing Matters—0
CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation—0
Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models—0
Automating lichen monitoring in ecological studies using instance segmentation of time-lapse images—0
Gramian Attention Heads are Strong yet Efficient Vision LearnersCode0
Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model—0
MSFormer: A Skeleton-multiview Fusion Method For Tooth Instance Segmentation—0
Deep Learning Techniques for Video Instance Segmentation: A Survey—0
Panoptic Out-of-Distribution Segmentation—0
Hierarchical Side-Tuning for Vision Transformers—0
SimPLR: A Simple and Plain Transformer for Scaling-Efficient Object Detection and Segmentation—0
Enhancing Representations through Heterogeneous Self-Supervised Learning—0
Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform—0
Cross-Task Data Augmentation by Pseudo-label Generation for Region Based Coronary Artery Instance Segmentation—0
ConvNeXtv2 Fusion with Mask R-CNN for Automatic Region Based Coronary Artery Stenosis Detection for Disease DiagnosisCode0
CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation—0
Combining Datasets with Different Label Sets for Improved Nucleus Segmentation and Classification—0
LoCUS: Learning Multiscale 3D-consistent Features from Posed Images—0
Adapting Vision Foundation Models for Plant Phenotyping—0
Self-supervised Learning of Contextualized Local Visual EmbeddingsCode0
Advances in Kidney Biopsy Lesion Assessment through Dense Instance Segmentation—0
CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding—0
Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Clouds—0
Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling—0
Automatic Animation of Hair Blowing in Still Portrait Photos—0
A SAM-based Solution for Hierarchical Panoptic Segmentation of Crops and Weeds Competition—0
Show:102550
← PrevPage 25 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
8GLEE-Promask AP54.2—Unverified
9ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2—Unverified
10SwinV2-G (HTC++)mask AP53.7—Unverified