List your company
ResearchFormerly WizWand

Open-vocabulary Segmentation on PASCAL Context

36.8mIoU+CS & AMF (GCLIP)
8.09615.5482330.452Aug 27, 2024Nov 20, 2024Feb 13, 2025May 9, 2025Aug 2, 2025Oct 26, 2025Jan 20, 2026
Updated 5mo ago

Evaluation results

MethodLinks
+CS & AMF (GCLIP)Pub. & Year=Ours, Setting=TF-OVSS2025.0236.8
+CSPub. & Year=Ours, Setting=TF-OVSS2025.0236.2
GEM‡Pub. & Year=CVPR’24, Setting=TF-OVSS2025.0235.9
ClearCLIPPub. & Year=ECCV’24, Setting=TF-OVSS2025.0235.9
CLIPtrasePub. & Year=ECCV’24, Setting=TF-OVSS2025.0234.9
SCLIPPub. & Year=ECCV’24, Setting=TF-OVSS2025.0234.2
ReCLIPPub. & Year=CVPR’24, Setting=USS2025.0233.8
CLIP-S4Pub. & Year=CVPR’23, Setting=USS2025.0233.6
INSIGHT_thresParadigm=Use Frozen CLIP with Interpretability, Background Prompt=Yes2026.0133.2
CLIP-DINOiserParadigm=Use Frozen CLIP, Background Prompt=Yes, Protocol=Rerun (*)2026.0132.5
MaskCLIP+†Pub. & Year=ECCV’22, Setting=USS2025.0231.1
ProMaCVenue=Ours, Segmentation Annotation=-, Extra Text pairs=-2024.0830.7
TCLPub. & Year=CVPR’23, Setting=T-OVSS2025.0230.3
OVDiffParadigm=Build prototypes per class, Extra Backbones=DINO & SD, Background Prompt=Yes2026.0130.1
INSIGHTParadigm=Use Frozen CLIP with Interpretability, Background Prompt=Yes2026.0128.9
SegCLIPVenue=ICML23, Segmentation Annotation=COCO [35], Extra Text pairs=CC [48]2024.0824.7
SegCLIPParadigm=Text/image alignment training with captions, Background Prompt=Yes2026.0124.7
TCLVenue=CVPR23, Segmentation Annotation=-, Extra Text pairs=CC3M [48], CC12M [7]2024.0824.3
TCLParadigm=Text/image alignment training with captions, Background Prompt=Yes2026.0124.3
MaskCLIPParadigm=Use Frozen CLIP, Extra Backbones=ref[9], Background Prompt=Yes2026.0124
MaskCLIPVenue=ECCV22, Segmentation Annotation=-, Extra Text pairs=-2024.0823.6
GroupViT‡Pub. & Year=CVPR’22, Setting=T-OVSS2025.0223.4
ViewCoVenue=ICLR23, Segmentation Annotation=-, Extra Text pairs=CC12M [7], YFCC14M [53]2024.0823
MaskCLIPParadigm=Use Frozen CLIP, Background Prompt=Yes2026.0122.9
GroupViTVenue=CVPR22, Segmentation Annotation=-, Extra Text pairs=CC12M [7], YFCC14M [53]2024.0822.4
ZeroSegParadigm=Text/image alignment training with captions, Background Prompt=Yes2026.0121.8
MaskCLIP†Pub. & Year=ECCV’22, Setting=TF-OVSS2025.0221.7
OVSegmentorVenue=CVPR23, Segmentation Annotation=-, Extra Text pairs=CC12M [7]2024.0820.4
OVSegmentorParadigm=Text/image alignment training with captions, Background Prompt=Yes2026.0120.4
ReCoParadigm=Build prototypes per class, Background Prompt=Yes2026.0119.9
CLIP-DIYParadigm=Use Frozen CLIP, Extra Backbones=DINO, Background Prompt=Yes2026.0119.7
GroupViTParadigm=Text/image alignment training with captions, Background Prompt=Yes2026.0118.7
CLIP‡Pub. & Year=ICML’21, Setting=TF-OVSS2025.029.2