SOTAVerified

Segmentation

Papers

Showing 326350 of 13072 papers

TitleStatusHype
Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and LocalizationCode2
Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differencesCode2
Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite ImageryCode2
DeepGCNs: Making GCNs Go as Deep as CNNsCode2
HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal ModelCode2
Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial ImageryCode2
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic SegmentationCode2
Hybrid-Segmentor: A Hybrid Approach to Automated Fine-Grained Crack Segmentation in Civil InfrastructureCode2
HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual PerceiverCode2
Improving Semantic Segmentation via Video Propagation and Label RelaxationCode2
In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic SegmentationCode2
A Pilot Study for Chinese SQL Semantic ParsingCode2
Deep Hierarchical Semantic SegmentationCode2
Interactive4D: Interactive 4D LiDAR SegmentationCode2
Delivering Arbitrary-Modal Semantic SegmentationCode2
Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union LearningCode2
Label Efficient Visual Abstractions for Autonomous DrivingCode2
DiffRect: Latent Diffusion Label Rectification for Semi-supervised Medical Image SegmentationCode2
LaSagnA: Language-based Segmentation Assistant for Complex QueriesCode2
Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image SegmentationCode2
Learning-Based Defect Recognitions for Autonomous UAV InspectionsCode2
LesionLocator: Zero-Shot Universal Tumor Segmentation and Tracking in 3D Whole-Body ImagingCode2
Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable SegmentationCode2
ASAM: Boosting Segment Anything Model with Adversarial TuningCode2
AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three WeeksCode2
Show:102550
← PrevPage 14 of 523Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1unSAM+ (Semi-supervised)Average Precision42.8Unverified
2SAMAverage Precision38.9Unverified
#ModelMetricClaimedVerifiedStatus
1HNN10%20Unverified
#ModelMetricClaimedVerifiedStatus
1ABANetF1 Score96.82Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50 + DeepLabV3+F1 score0.77Unverified
#ModelMetricClaimedVerifiedStatus
1LangGasIoU0.69Unverified