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 501525 of 2262 papers

TitleStatusHype
SeqFormer: Sequential Transformer for Video Instance SegmentationCode1
PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM ConnectomicsCode1
Implicit Feature Refinement for Instance SegmentationCode1
VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance SegmentationCode1
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
DenseCLIP: Language-Guided Dense Prediction with Context-Aware PromptingCode1
Container: Context Aggregation NetworksCode1
PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite ImagesCode1
End-to-End Referring Video Object Segmentation with Multimodal TransformersCode1
Contrastive Object-level Pre-training with Spatial Noise Curriculum LearningCode1
Mask Transfiner for High-Quality Instance SegmentationCode1
BoxeR: Box-Attention for 2D and 3D TransformersCode1
Conditional Object-Centric Learning from VideoCode1
Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-LabelingCode1
Depth-aware Object Segmentation and Grasp Detection for Robotic Picking TasksCode1
Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing ImagesCode1
Panoptic Segmentation: A ReviewCode1
TransMix: Attend to Mix for Vision TransformersCode1
Swin Transformer V2: Scaling Up Capacity and ResolutionCode1
iBOT: Image BERT Pre-Training with Online TokenizerCode1
Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2Code1
ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity TrackingCode1
Panoptic 3D Scene Reconstruction From a Single RGB ImageCode1
PointNu-Net: Keypoint-assisted Convolutional Neural Network for Simultaneous Multi-tissue Histology Nuclei Segmentation and ClassificationCode1
A Survey of Self-Supervised and Few-Shot Object DetectionCode1
Show:102550
← PrevPage 21 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