SOTAVerified

Zero Shot Segmentation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 134 papers

TitleStatusHype
The Emergence of Objectness: Learning Zero-Shot Segmentation from VideosCode1
TomoSAM: a 3D Slicer extension using SAM for tomography segmentationCode1
TongueSAM: An Universal Tongue Segmentation Model Based on SAM with Zero-ShotCode1
Training-free Object Counting with PromptsCode1
ZegOT: Zero-shot Segmentation Through Optimal Transport of Text PromptsCode1
Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model EstimationCode1
Zero-Shot Tree Detection and Segmentation from Aerial Forest ImageryCode1
HOLa: HoloLens Object LabelingCode0
X-Recon: Learning-based Patient-specific High-Resolution CT Reconstruction from Orthogonal X-Ray ImagesCode0
SimSAM: Zero-shot Medical Image Segmentation via Simulated InteractionCode0
PanSAM: Zero-Shot, Prompt-Free Pancreas Segmentation in CT ImagingCode0
3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic GapCode0
PaveCap: The First Multimodal Framework for Comprehensive Pavement Condition Assessment with Dense Captioning and PCI EstimationCode0
Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)Code0
Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation OnlyCode0
OpenSD: Unified Open-Vocabulary Segmentation and DetectionCode0
A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic SegmentationCode0
Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast ObjectsCode0
Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic DataCode0
Removing Watermarks with Partial Regeneration using Semantic InformationCode0
PaveSAM Segment Anything for Pavement Distress—0
Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery—0
Computer-Vision Benchmark Segment-Anything Model (SAM) in Medical Images: Accuracy in 12 Datasets—0
Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentation—0
Visual and Text Prompt Segmentation: A Novel Multi-Model Framework for Remote Sensing—0
Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond—0
Resilience of Vision Transformers for Domain Generalisation in the Presence of Out-of-Distribution Noisy Images—0
A Simple Framework for Open-Vocabulary Zero-Shot Segmentation—0
SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation—0
SAM3D: Zero-Shot Semi-Automatic Segmentation in 3D Medical Images with the Segment Anything Model—0
SAM for Poultry Science—0
SAM-SP: Self-Prompting Makes SAM Great Again—0
SANeRF-HQ: Segment Anything for NeRF in High Quality—0
SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model—0
Segment Anything in High Quality—0
Segment Anything Meets Semantic Communication—0
Zero-shot spatial layout conditioning for text-to-image diffusion models—0
ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation—0
Pedestrian Accessible Infrastructure Inventory: Assessing Zero-Shot Segmentation on Multi-Mode Geospatial Data for All Pedestrian Types—0
Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging—0
Segment to Recognize Robustly -- Enhancing Recognition by Image Decomposition—0
All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning—0
Self-supervised Tumor Segmentation through Layer Decomposition—0
Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models—0
AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation—0
SILC: Improving Vision Language Pretraining with Self-Distillation—0
SmartScan: An AI-based Interactive Framework for Automated Region Extraction from Satellite Images—0
SOS-Match: Segmentation for Open-Set Robust Correspondence Search and Robot Localization in Unstructured Environments—0
Exploring Open-Vocabulary Semantic Segmentation without Human Labels—0
Eye on the Target: Eye Tracking Meets Rodent Tracking—0
Show:102550
← PrevPage 2 of 3Next →
All datasetsSegmentation in the WildADE20K training-free zero-shot segmentation

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Grounded HQ-SAMMean AP49.6—Unverified
2Grounded-SAMMean AP46—Unverified
3UNINEXTMean AP42.1—Unverified
4HIPIEMean AP41.6—Unverified
5SANMean AP41.4—Unverified
6odiseMean AP38.7—Unverified
7OpenSEEDMean AP36.1—Unverified
8OpenSDMean AP35.8—Unverified
9SGinW_Team (X-Decoder-L)Mean AP32.2—Unverified
10SGinW_Team (X-Decoder-B)Mean AP27.7—Unverified
#ModelMetricClaimedVerifiedStatus
1COSMOS ViT-B/16mIoU17.7—Unverified
2GEM (MetaCLIP)mIoU17.1—Unverified
3GEM (CLIP)mIoU15.7—Unverified
4CLIPSurgerymIoU12.9—Unverified
5MaskCLIPmIoU10.2—Unverified