SOTAVerified

Zero Shot Segmentation

Papers

Showing 5175 of 134 papers

TitleStatusHype
DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized CutCode2
SimSAM: Zero-shot Medical Image Segmentation via Simulated InteractionCode0
Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding0
SAM3D: Zero-Shot Semi-Automatic Segmentation in 3D Medical Images with the Segment Anything Model0
Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear StructuresCode1
Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery0
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies0
Gaga: Group Any Gaussians via 3D-aware Memory Bank0
Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image SegmentationCode2
AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation0
MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image SegmentationCode2
Quantifying uncertainty in lung cancer segmentation with foundation models applied to mixed-domain datasets0
Multi-Grained Cross-modal Alignment for Learning Open-vocabulary Semantic Segmentation from Text Supervision0
Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic DataCode0
From Generalization to Precision: Exploring SAM for Tool Segmentation in Surgical Environments0
TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human AnnotationCode1
Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation0
MatSAM: Efficient Extraction of Microstructures of Materials via Visual Large ModelCode1
SOS-Match: Segmentation for Open-Set Robust Correspondence Search and Robot Localization in Unstructured Environments0
Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion0
Spectral Prompt Tuning:Unveiling Unseen Classes for Zero-Shot Semantic SegmentationCode1
Testing the Segment Anything Model on radiology data0
OpenSD: Unified Open-Vocabulary Segmentation and DetectionCode0
SANeRF-HQ: Segment Anything for NeRF in High Quality0
Grounding Everything: Emerging Localization Properties in Vision-Language TransformersCode1
Show:102550
← PrevPage 3 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Grounded HQ-SAMMean AP49.6Unverified
2Grounded-SAMMean AP46Unverified
3UNINEXTMean AP42.1Unverified
4HIPIEMean AP41.6Unverified
5SANMean AP41.4Unverified
6odiseMean AP38.7Unverified
7OpenSEEDMean AP36.1Unverified
8OpenSDMean AP35.8Unverified
9SGinW_Team (X-Decoder-L)Mean AP32.2Unverified
10SGinW_Team (X-Decoder-B)Mean AP27.7Unverified
#ModelMetricClaimedVerifiedStatus
1COSMOS ViT-B/16mIoU17.7Unverified
2GEM (MetaCLIP)mIoU17.1Unverified
3GEM (CLIP)mIoU15.7Unverified
4CLIPSurgerymIoU12.9Unverified
5MaskCLIPmIoU10.2Unverified