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 201225 of 2262 papers

TitleStatusHype
Unified Embedding Alignment for Open-Vocabulary Video Instance SegmentationCode1
Multi-Grained Contrast for Data-Efficient Unsupervised Representation LearningCode1
Instance Consistency Regularization for Semi-Supervised 3D Instance SegmentationCode1
CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic SurgeryCode1
OoDIS: Anomaly Instance Segmentation BenchmarkCode1
Scaling Graph Convolutions for Mobile VisionCode1
Instance Segmentation and Teeth Classification in Panoramic X-raysCode1
PerSense: Personalized Instance Segmentation in Dense ImagesCode1
AugmenTory: A Fast and Flexible Polygon Augmentation LibraryCode1
UniFS: Universal Few-shot Instance Perception with Point RepresentationsCode1
Surgical-DeSAM: Decoupling SAM for Instrument Segmentation in Robotic SurgeryCode1
FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous DrivingCode1
The devil is in the object boundary: towards annotation-free instance segmentation using Foundation ModelsCode1
SEVD: Synthetic Event-based Vision Dataset for Ego and Fixed Traffic PerceptionCode1
Let-It-Flow: Simultaneous Optimization of 3D Flow and Object ClusteringCode1
Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series AnalysisCode1
AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D ScansCode1
BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance SegmentationCode1
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance SegmentationCode1
StainFuser: Controlling Diffusion for Faster Neural Style Transfer in Multi-Gigapixel Histology ImagesCode1
When Semantic Segmentation Meets Frequency AliasingCode1
End-to-End Human Instance MattingCode1
ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual ConnectionsCode1
TDViT: Temporal Dilated Video Transformer for Dense Video TasksCode1
Complete Instances Mining for Weakly Supervised Instance SegmentationCode1
Show:102550
← PrevPage 9 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
8GLEE-Promask AP54.2Unverified
9ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2Unverified
10SwinV2-G (HTC++)mask AP53.7Unverified