List your company

Open Vocabulary Semantic Segmentation on PASCAL VOC VOC21 with background 2012

70.8mIoUTrident
6.3223.0639.856.54Nov 14, 2024Feb 13, 2025May 16, 2025Aug 16, 2025Nov 16, 2025Feb 16, 2026May 19, 2026

Evaluation results

MethodLinks
TridentTrain=false, Backbone=ViT-H/142024.1170.8
TridentTrain=false, Backbone=ViT-B/162024.1167.1
OVDiffTrain=false, Backbone=ViT-B/162024.1166.3
ProxyCLIPTrain=false, Backbone=ViT-H/142024.1165
PEARLPub. & Year=current, Extra data=✗, Extra backbone=✗, Training free=✓2026.0364.1
CASS*Pub. & Year=CVPR’25, Extra data=✗, Extra backbone=DINOv3 (ViT-B/16), Training free=✓2026.0362.3
CLIP-DINOiserTrain=true2024.1162.1
CLIP-DINOiserPub. & Year=ECCV’24, Extra data=ImageNet-1K, Extra backbone=DINOv1 (ViT-B/16), Training free=✗2026.0362.1
LaVGPub. & Year=ECCV’24, Extra data=✗, Extra backbone=DINOv1 (ViT-B/8), Training free=✓2026.0362.1
ProxyCLIPTrain=false, Backbone=ViT-B/162024.1161.3
TTDTrain=true2024.1161.1
LPOSS*Pub. & Year=CVPR’25, Extra data=✗, Extra backbone=DINOv1 (ViT-B/16), Training free=✓2026.0361.1
SAM-CLIPTrain=true2024.1160.6
SAM-CLIPPub. & Year=CVPR’24, Extra data=Merged-41M, Extra backbone=SAMv1 (ViT-B/16), Training free=✗2026.0360.6
SCLIPTrain=false, Backbone=ViT-B/162024.1159.1
SCLIP*Pub. & Year=ECCV’24, Extra data=✗, Extra backbone=✗, Training free=✓2026.0359.1
NACLIPTrain=false, Backbone=ViT-B/162024.1158.9
NACLIP*Pub. & Year=WACV’25, Extra data=✗, Extra backbone=✗, Training free=✓2026.0358.9
ProxyCLIP*Pub. & Year=ECCV’24, Extra data=✗, Extra backbone=DINOv2† (ViT-B/14), Training free=✓2026.0358.6
CASS*Pub. & Year=CVPR’25, Extra data=✗, Extra backbone=DINOv2† (ViT-B/14), Training free=✓2026.0358.6
CoDeTrain=true2024.1157.7
CoDePub. & Year=CVPR’24, Extra data=CC3M+RedCaps, Extra backbone=✗, Training free=✗2026.0357.7
SFP*Pub. & Year=ICCV’25, Extra data=✗, Extra backbone=✗, Training free=✓2026.0356.8
ClearCLIPPub. & Year=ECCV’24, Extra data=✗, Extra backbone=✗, Training free=✓2026.0351.8
FreeDAPub. & Year=CVPR’24, Extra data=COCO Captions, Extra backbone=DINOv2 (ViT-B/14), Training free=✓2026.0351.7
SigLIPv2 + UniRefinerViT=So/16, Background category=With background category, Protocol=Zero-shot2026.0551.3
TCLTrain=true2024.1151.2
TCLPub. & Year=CVPR’23, Extra data=CC3M+CC12M, Extra backbone=✗, Training free=✗2026.0351.2
CLIPtrasePub. & Year=ECCV’24, Extra data=✗, Extra backbone=✗, Training free=✓2026.0350.9
GroupViTPub. & Year=CVPR’22, Extra data=CC12M+RedCaps, Extra backbone=✗, Training free=✗2026.0350.4
CaRPub. & Year=CVPR’24, Extra data=✗, Extra backbone=✗, Training free=✓2026.0348.6
EVA-CLIP + UniRefinerViT=8B/14, Background category=With background category, Protocol=Zero-shot2026.0546.4
GEMPub. & Year=CVPR’24, Extra data=✗, Extra backbone=✗, Training free=✓2026.0346.2
CLIP + UniRefinerViT=G/14, Background category=With background category, Protocol=Zero-shot2026.0545.7
SCLIPTrain=false, Backbone=ViT-H/142024.1143.8
MaskCLIPTrain=false, Backbone=ViT-B/162024.1143.4
CLIPViT=G/14, Background category=With background category, Protocol=Zero-shot2026.0542.7
MaskCLIPPub. & Year=ECCV’22, Extra data=✗, Extra backbone=✗, Training free=✓2026.0338.3
SigLIPv2ViT=So/16, Background category=With background category, Protocol=Zero-shot2026.0535.5
MaskCLIPTrain=false, Backbone=ViT-H/142024.1131.4
ReCoTrain=false, Backbone=ViT-B/162024.1125.1
ReCoPub. & Year=NeurIPS’22, Extra data=ImageNet-1K, Extra backbone=✗, Training free=✓2026.0325.1
EVA-CLIPViT=8B/14, Background category=With background category, Protocol=Zero-shot2026.0524.5
CLIPPub. & Year=ICML’21, Extra data=✗, Extra backbone=✗, Training free=✓2026.0318.6
CLIPTrain=false, Backbone=ViT-B/162024.1116.4
OpenCLIPTrain=false, Backbone=ViT-H/142024.118.8