SOTAVerified

Segmentation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3676–3700 of 13072 papers

TitleStatusHype
BIT: Bi-Level Temporal Modeling for Efficient Supervised Action Segmentation—0
AutoProSAM: Automated Prompting SAM for 3D Multi-Organ SegmentationCode0
Multilayer Multiset Neuronal Networks -- MMNNs—0
Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample AssessmentCode0
LAC: Latent Action Composition for Skeleton-based Action Segmentation—0
Local-Global Pseudo-label Correction for Source-free Domain Adaptive Medical Image Segmentation—0
1st Place Solution for the 5th LSVOS Challenge: Video Instance SegmentationCode1
SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstruction—0
Referring Image Segmentation Using Text SupervisionCode1
Attention-Guided Lidar Segmentation and Odometry Using Image-to-Point Cloud Saliency TransferCode0
VideoCutLER: Surprisingly Simple Unsupervised Video Instance SegmentationCode3
Semi-Supervised Learning for Visual Bird's Eye View Semantic SegmentationCode1
VesselShot: Few-shot learning for cerebral blood vessel segmentation—0
Ensemble of Anchor-Free Models for Robust Bangla Document Layout Segmentation—0
Cheap Lunch for Medical Image Segmentation by Fine-tuning SAM on Few Exemplars—0
Enhancing Bloodstain Analysis Through AI-Based Segmentation: Leveraging Segment Anything Model for Crime Scene InvestigationCode0
Transfer Learning for Microstructure Segmentation with CS-UNet: A Hybrid Algorithm with Transformer and CNN EncodersCode1
ReFuSeg: Regularized Multi-Modal Fusion for Precise Brain Tumour Segmentation—0
Semi-Supervised Semantic Segmentation via Marginal Contextual InformationCode0
PE-MED: Prompt Enhancement for Interactive Medical Image Segmentation—0
SamDSK: Combining Segment Anything Model with Domain-Specific Knowledge for Semi-Supervised Learning in Medical Image SegmentationCode1
Self-supervised Scene Text Segmentation with Object-centric Layered Representations Augmented by Text Regions—0
Deep learning-based interactive segmentation in remote sensingCode0
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and SegmentationCode1
A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic SegmentationCode1
Show:102550
← PrevPage 148 of 523Next →
All datasetsSA-1B.MFSDMMFloodSimGas

Benchmark Results

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