SOTAVerified

Zero-Shot Semantic Segmentation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 60 papers

TitleStatusHype
Split Matching for Inductive Zero-shot Semantic Segmentation—0
3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic GapCode0
Bridge the Gap Between Visual and Linguistic Comprehension for Generalized Zero-shot Semantic Segmentation—0
Disentangling CLIP for Multi-Object Perception—0
FLAIR: VLM with Fine-grained Language-informed Image RepresentationsCode2
Open-RGBT: Open-vocabulary RGB-T Zero-shot Semantic Segmentation in Open-world Environments—0
Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO—0
OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained UnderstandingCode1
DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized CutCode2
Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic SegmentationCode2
AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation—0
Semantics from Space: Satellite-Guided Thermal Semantic Segmentation Annotation for Aerial Field RobotsCode0
OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic SegmentationCode1
Annotation Free Semantic Segmentation with Vision Foundation Models—0
Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation—0
Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation—0
Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship DescriptorsCode0
Exploring Regional Clues in CLIP for Zero-Shot Semantic SegmentationCode3
Spectral Prompt Tuning:Unveiling Unseen Classes for Zero-Shot Semantic SegmentationCode1
CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen—0
SCLIP: Rethinking Self-Attention for Dense Vision-Language InferenceCode1
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding—0
CLIP Is Also a Good Teacher: A New Learning Framework for Inductive Zero-shot Semantic Segmentation—0
An easy zero-shot learning combination: Texture Sensitive Semantic Segmentation IceHrNet and Advanced Style Transfer Learning StrategyCode0
CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-FreeCode1
Show:102550
← PrevPage 1 of 3Next →
All datasetsCOCO-StuffMESSPASCAL VOCADE20K-847

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OTSeg+Transductive Setting hIoU49.8—Unverified
2CLIP-RCTransductive Setting hIoU49.7—Unverified
3OTSegTransductive Setting hIoU49.5—Unverified
4ZegCLIPTransductive Setting hIoU48.5—Unverified
5MVP-SEG+Transductive Setting hIoU45.5—Unverified
6FreeSegTransductive Setting hIoU45.3—Unverified
7MaskCLIP+Transductive Setting hIoU45—Unverified
8zssegTransductive Setting hIoU41.5—Unverified
9DeOPInductive Setting hIoU38.2—Unverified
10STRICTTransductive Setting hIoU34.8—Unverified
#ModelMetricClaimedVerifiedStatus
1CAT-Seg-LMean IoU38.14—Unverified
2CAT-Seg-HMean IoU35.66—Unverified
3CAT-Seg-BMean IoU33.74—Unverified
4SAN-LMean IoU30.06—Unverified
5Grounded-SAM-LMean IoU29.05—Unverified
6Grounded-SAM-HMean IoU28.78—Unverified
7Grounded-SAM-BMean IoU28.52—Unverified
8OVSeg-LMean IoU26.94—Unverified
9SAN-BMean IoU26.74—Unverified
10OpenSeeD-TMean IoU24.33—Unverified
#ModelMetricClaimedVerifiedStatus
1OTSeg+Transductive Setting hIoU94.4—Unverified
2OTSegTransductive Setting hIoU94.2—Unverified
3CLIP-RCTransductive Setting hIoU93—Unverified
4ZegCLIPTransductive Setting hIoU91.1—Unverified
5MaskCLIP+Transductive Setting hIoU87.4—Unverified
6FreeSegTransductive Setting hIoU86.9—Unverified
7DeOpInductive Setting hIoU80.8—Unverified
8zssegTransductive Setting hIoU79.3—Unverified
9ZegFormerInductive Setting hIoU73.3—Unverified
10STRICTTransductive Setting hIoU49.8—Unverified
#ModelMetricClaimedVerifiedStatus
1MAFTunseen mIoU8.7—Unverified