SOTAVerified

Open Vocabulary Semantic Segmentation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 113 papers

TitleStatusHype
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive ReinforcementCode4
SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing ImagesCode3
SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation ImageryCode3
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary SegmentationCode2
HyperSeg: Towards Universal Visual Segmentation with Large Language ModelCode2
CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic SegmentationCode2
In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic SegmentationCode2
ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary SegmentationCode2
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary SegmentationCode2
A Unified Framework for 3D Scene UnderstandingCode2
Understanding Multi-Granularity for Open-Vocabulary Part SegmentationCode2
Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic SegmentationCode2
PosSAM: Panoptic Open-vocabulary Segment AnythingCode2
CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentationCode2
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense PredictionCode2
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPCode2
SAD: Segment Any RGBDCode2
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic SegmentationCode2
Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion ModelsCode2
Side Adapter Network for Open-Vocabulary Semantic SegmentationCode2
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPCode2
ReME: A Data-Centric Framework for Training-Free Open-Vocabulary SegmentationCode1
Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic SegmentationCode1
Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic SegmentationCode1
OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual ReasoningCode1
Show:102550
← PrevPage 1 of 5Next →
All datasetsPASCAL Context-59ADE20K-150ADE20K-847PascalVOC-20PASCAL Context-459COCO-Stuff-171CityscapesPascalVOC-20biSAIDCityscape-171FASTISPRS Potsdam

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HyperSegmIoU64.6—Unverified
2SILCmIoU63.5—Unverified
3CAT-SegmIoU63.3—Unverified
4MaskCLIP++mIoU62.5—Unverified
5CLIPSelfmIoU62.3—Unverified
6UMG-CLIP-L/14mIoU61—Unverified
7SEDmIoU60.6—Unverified
8Mask-AdaptermIoU60.4—Unverified
9EBSeg-LmIoU60.2—Unverified
10MAFT+mIoU59.4—Unverified
#ModelMetricClaimedVerifiedStatus
1UMG-CLIP-E/14mIoU38.2—Unverified
2Mask-AdaptermIoU38.2—Unverified
3MaskCLIP++mIoU38.2—Unverified
4CAT-SegmIoU37.9—Unverified
5SILCmIoU37.7—Unverified
6MAFT+mIoU36.1—Unverified
7UMG-CLIP-L/14mIoU36.1—Unverified
8OVSeg + OpenDASmIoU35.8—Unverified
9SEDmIoU35.2—Unverified
10CLIPSelfmIoU34.5—Unverified
#ModelMetricClaimedVerifiedStatus
1UMG-CLIP-E/14mIoU17.3—Unverified
2MaskCLIP++mIoU16.8—Unverified
3Mask-AdaptermIoU16.2—Unverified
4CAT-SegmIoU16—Unverified
5UMG-CLIP-L/14mIoU15.4—Unverified
6MAFT+mIoU15.1—Unverified
7SILCmIoU15—Unverified
8PosSAMmIoU14.9—Unverified
9FC-CLIPmIoU14.8—Unverified
10SCANmIoU14—Unverified
#ModelMetricClaimedVerifiedStatus
1UMG-CLIP-L/14mIoU97.9—Unverified
2SILCmIoU97.6—Unverified
3SCANmIoU97.2—Unverified
4CAT-SegmIoU97—Unverified
5MaskCLIP++mIoU96.8—Unverified
6MAFT+mIoU96.5—Unverified
7EBSeg-LmIoU96.4—Unverified
8FC-CLIPmIoU95.4—Unverified
9OVSeg Swin-BmIoU94.5—Unverified
10MAFT-ViTLmIoU92.1—Unverified
#ModelMetricClaimedVerifiedStatus
1SILCmIoU25.8—Unverified
2UMG-CLIP-E/14mIoU25.2—Unverified
3MaskCLIP++mIoU23.9—Unverified
4CAT-SegmIoU23.8—Unverified
5UMG-CLIP-L/14mIoU23.2—Unverified
6Mask-AdaptermIoU22.7—Unverified
7SEDmIoU22.6—Unverified
8MAFT+mIoU21.6—Unverified
9EBSeg-LmIoU21—Unverified
10FC-CLIPmIoU18.2—Unverified
#ModelMetricClaimedVerifiedStatus
1POMPHIoU39.1—Unverified
2ZSSegHIoU37.8—Unverified
3ZegFormerHIoU34.8—Unverified
4TTD (TCL)mIoU23.7—Unverified
5LaVGmIoU23.2—Unverified
6CLIP Surgery (original CLIP without any fine-tuning)mIoU21.9—Unverified
7TTD (MaskCLIP)mIoU19.4—Unverified
#ModelMetricClaimedVerifiedStatus
1FC-CLIPmIoU56.2—Unverified
2SimSegmIoU34.5—Unverified
3TTD (TCL)mIoU32—Unverified
4CLIP Surgery (CLIP without any fine-tuning)mIoU31.4—Unverified
5TTD (MaskCLIP)mIoU27—Unverified
#ModelMetricClaimedVerifiedStatus
1UMG-CLIP-E/14mIoU85.4—Unverified
2CAT-SegmIoU82.5—Unverified
3SILCmIoU82.5—Unverified
4FC-CLIPmIoU81.8—Unverified
#ModelMetricClaimedVerifiedStatus
1SkySense-OmIoU-43.9—Unverified
2SegEarth-OVmIoU-21.7—Unverified
#ModelMetricClaimedVerifiedStatus
1PACLmIoU38.8—Unverified
#ModelMetricClaimedVerifiedStatus
1SkySense-OmIoU8.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SkySense-OmIoU54.1—Unverified
#ModelMetricClaimedVerifiedStatus
1SkySense-OmIoU30.89—Unverified
#ModelMetricClaimedVerifiedStatus
1SkySense-OmIoU32.12—Unverified