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 301350 of 2262 papers

TitleStatusHype
CryoNuSeg: A Dataset for Nuclei Instance Segmentation of Cryosectioned H&E-Stained Histological ImagesCode1
Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance SegmentationCode1
Graph Relation Distillation for Efficient Biomedical Instance SegmentationCode1
Hi4D: 4D Instance Segmentation of Close Human InteractionCode1
BoxeR: Box-Attention for 2D and 3D TransformersCode1
FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous DrivingCode1
Focal Self-attention for Local-Global Interactions in Vision TransformersCode1
Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive FusionCode1
Contrastive Object-level Pre-training with Spatial Noise Curriculum LearningCode1
BoundarySqueeze: Image Segmentation as Boundary SqueezingCode1
Boundary-preserving Mask R-CNNCode1
ContrastMask: Contrastive Learning to Segment Every ThingCode1
COVID-CT-Mask-Net: Prediction of COVID-19 from CT Scans Using Regional FeaturesCode1
FoodSAM: Any Food SegmentationCode1
ConvMLP: Hierarchical Convolutional MLPs for VisionCode1
An Instance Segmentation Dataset of Yeast Cells in MicrostructuresCode1
Boundary-aware Contrastive Learning for Semi-supervised Nuclei Instance SegmentationCode1
Co-Scale Conv-Attentional Image TransformersCode1
Continuous Copy-Paste for One-Stage Multi-Object Tracking and SegmentationCode1
Boundary-assisted Region Proposal Networks for Nucleus SegmentationCode1
BoxSnake: Polygonal Instance Segmentation with Box SupervisionCode1
A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection from Aerial ImagesCode1
BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance SegmentationCode1
BoxVIS: Video Instance Segmentation with Box AnnotationsCode1
ContourFormer:Real-Time Contour-Based End-to-End Instance Segmentation TransformerCode1
Contextual Transformer Networks for Visual RecognitionCode1
Contour Proposal Networks for Biomedical Instance SegmentationCode1
Context-Aware Relative Object Queries To Unify Video Instance and Panoptic SegmentationCode1
Continual Learning for Image Segmentation with Dynamic QueryCode1
CTVIS: Consistent Training for Online Video Instance SegmentationCode1
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode1
CycleMLP: A MLP-like Architecture for Dense PredictionCode1
BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance SegmentationCode1
Cyclic Learning: Bridging Image-level Labels and Nuclei Instance SegmentationCode1
FinnWoodlands DatasetCode1
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance SegmentationCode1
Conditional Object-Centric Learning from VideoCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Container: Context Aggregation NetworksCode1
Compositional Human-Scene Interaction Synthesis with Semantic ControlCode1
Decoupling Classifier for Boosting Few-shot Object Detection and Instance SegmentationCode1
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance SegmentationCode1
Conditional Convolutions for Instance SegmentationCode1
A One Stop 3D Target Reconstruction and multilevel Segmentation MethodCode1
Deep learning approaches to building rooftop thermal bridge detection from aerial imagesCode1
Container: Context Aggregation NetworkCode1
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm QuantizerCode1
Deep Learning based Food Instance Segmentation using Synthetic DataCode1
BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online PoliciesCode1
BlendMask: Top-Down Meets Bottom-Up for Instance SegmentationCode1
Show:102550
← PrevPage 7 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