List your company
ResearchFormerly WizWand

Semantic Segmentation on VOC21

84.6mIoUODISE
20.84837.39953.9570.501Nov 24, 2024Feb 16, 2025May 11, 2025Aug 3, 2025Oct 26, 2025Jan 18, 2026Apr 13, 2026
Updated 6mo ago

Evaluation results

MethodLinks
ODISEBackbone=ViT-L/14, Training Set=COCO-Panoptic2025.0584.6
CAT-Seg+DeCLIPBackbone=ViT-L/14, Training Set=COCO-Stuff2025.0583.9
FrozenSegBackbone=ConvNeXt-L, Training Set=COCO-Panoptic2025.0582.5
CAT-SegBackbone=ViT-L/14, Training Set=COCO-Stuff2025.0582.5
FC-CLIPBackbone=ConvNeXt-L, Training Set=COCO-Panoptic2025.0581.8
CAT-Seg+DeCLIPBackbone=ViT-B/16, Training Set=COCO-Stuff2025.0581.3
CAT-SegBackbone=ViT-B/16, Training Set=COCO-Stuff2025.0577.3
CorrCLIPBackbone=ViT-L/14, Zero-shot=true2025.1276.7
CorrCLIPBackbone=ViT-B/16, Zero-shot=true2025.1274.8
CLIPer + ARMBackbone=ViT-B/16, Zero-shot=true2025.1273.2
CLIPer + ARMBackbone=ViT-L/14, Zero-shot=true2025.1271.6
CLIPerBackbone=ViT-L/14, Zero-shot=true2025.1269.8
SCLIP + ARMBackbone=ViT-B/16, Zero-shot=true2025.1269.5
DSLO (solve maximum velocity)Logits Model=CLIP ViT-L/142026.0468.9
DSLO (solve optimal path)Logits Model=CLIP ViT-L/142026.0468.2
DSLO (solve maximum velocity)Logits Model=CLIP ViT-B/162026.0467.8
DSLO (solve optimal path)Logits Model=CLIP ViT-B/162026.0466.9
OVDiffVenue=ECCV'242025.1266.3
CLIPerBackbone=ViT-B/16, Zero-shot=true2025.1265.9
SCLIP + ARMBackbone=ViT-L/14, Zero-shot=true2025.1265.8
CASSLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0465.8
ZegFormer+Backbone=ViT-B/16, Training Set=COCO-Stuff2025.0565.5
SC-CLIPLogits Model=CLIP ViT-L/14, Paradigm=M.M.2026.0465
SC-CLIPLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0464.6
NACLIPBackbone=ViT-B/16, Zero-shot=true2025.1264.1
ProxyCLIP + RAG-OVSVenue=This Paper2025.1262.9
LaVGLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0462.1
CLIP-DINOiser†Logits Model=CLIP ViT-B/16, Paradigm=I.T.2026.0462.1
SCLIP + RAG-OVSVenue=This Paper2025.1261.9
ProxyCLIPVenue=ECCV'242025.1261.3
NACLIP + ResCLIPTraining-free?=true, Encoder=ViT-B/162024.1161.1
ResCLIPBackbone=ViT-B/16, Zero-shot=true2025.1261.1
CLIP-Surgery + RAG-OVSVenue=This Paper2025.1261.1
SCLIP + ResCLIPTraining-free?=true, Encoder=ViT-B/162024.1160.7
NACLIP + RAG-OVSVenue=This Paper2025.1260.3
SCLIPTraining-free?=true, Encoder=ViT-B/162024.1159.1
SCLIPBackbone=ViT-B/16, Zero-shot=true2025.1259.1
SCLIPVenue=ECCV'242025.1259.1
SCLIPLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0459.1
ProxyCLIP‡Logits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0459.1
ClearCLIP + ResCLIPTraining-free?=true, Encoder=ViT-B/162024.1159
CLIP-SurgeryVenue=Pattern Recognition2025.1259
NACLIPTraining-free?=true, Encoder=ViT-B/162024.1158.9
NACLIPVenue=WACV'252025.1258.9
NACLIPLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0458.9
GEMLogits Model=CLIP ViT-B/16, Paradigm=I.T.2026.0458.7
ProxyCLIP‡Logits Model=CLIP ViT-L/14, Paradigm=M.M.2026.0458.1
CLIPtrace + RAG-OVSVenue=This Paper2025.1256.2
CLIPSurgeryLogits Model=CLIP ViT-B/16, Paradigm=I.T.2026.0455.2
TCLLogits Model=CLIP ViT-B/16, Paradigm=I.T.2026.0455
NACLIP + ResCLIPTraining-free?=true, Encoder=ViT-L/142024.1154.1
ResCLIPBackbone=ViT-L/14, Zero-shot=true2025.1254.1
OVSegmentorTraining-free?=false, Encoder=ViT-B/162024.1153.8
PGSegTraining-free?=false, Encoder=ViT-S/162024.1153.2
CLIPtraceVenue=ECCV'242025.1253
SCLIP + ResCLIPTraining-free?=true, Encoder=ViT-L/142024.1152.8
SegCLIPTraining-free?=false, Encoder=ViT-S/162024.1152.6
ViewCoTraining-free?=false, Encoder=ViT-S/162024.1152.4
GroupViTVenue=CVPR'222025.1252.3
NACLIPTraining-free?=true, Encoder=ViT-L/142024.1152.2
NACLIPLogits Model=CLIP ViT-L/14, Paradigm=M.M.2026.0452.1
ClearCLIPTraining-free?=true, Encoder=ViT-B/162024.1151.8
ClearCLIPBackbone=ViT-B/16, Zero-shot=true2025.1251.8
ClearCLIPLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0451.8
TCLTraining-free?=false, Encoder=ViT-B/162024.1151.2
CLIPtraseLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0450.9
ClearCLIP + ResCLIPTraining-free?=true, Encoder=ViT-L/142024.1150.7
GroupViTTraining-free?=false, Encoder=ViT-S/162024.1150.4
GroupViTLogits Model=CLIP ViT-B/16, Paradigm=I.T.2026.0450.4
ClearCLIPTraining-free?=true, Encoder=ViT-L/142024.1148.7
CaRLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0448.6
ClearCLIPLogits Model=CLIP ViT-L/14, Paradigm=M.M.2026.0448.6
CLIPSurgeryLogits Model=CLIP ViT-L/14, Paradigm=I.T.2026.0447.9
GEMTraining-free?=true, Encoder=ViT-B/162024.1146.2
ClearCLIPBackbone=ViT-L/14, Zero-shot=true2025.1246.1
GEMLogits Model=CLIP ViT-L/14, Paradigm=I.T.2026.0445.2
SCLIPTraining-free?=true, Encoder=ViT-L/142024.1144.4
SCLIPLogits Model=CLIP ViT-L/14, Paradigm=M.M.2026.0444.4
TIPSv2 L/14Model Scale=L, Patch Size=14, Zero-shot=true2026.0444.4
SCLIPBackbone=ViT-L/14, Zero-shot=true2025.1243.5
MaskCLIPVenue=ECCV'222025.1243.4
CoCuTraining-free?=false, Encoder=ViT-S/162024.1140.9
UNCHABackbone=ViT-S/16, Zero-shot=true2026.0339.03
MaskCLIPTraining-free?=true, Encoder=ViT-B/162024.1138.8
MaskCLIPBackbone=ViT-B/16, Zero-shot=true2025.1238.8
MaskCLIPLogits Model=CLIP ViT-B/16, Paradigm=I.T.2026.0438.3
HyCoCLIPBackbone=ViT-S/16, Zero-shot=true2026.0336.79
MERUBackbone=ViT-S/16, Zero-shot=true2026.0336.18
CLIPBackbone=ViT-S/16, Zero-shot=true2026.0336.02
UNCHABackbone=ViT-B/16, Zero-shot=true2026.0332.28
TIPS L/14Model Scale=L, Patch Size=14, Zero-shot=true2026.0430.5
CLIPBackbone=ViT-B/16, Zero-shot=true2026.0328.47
SigLIP2 SO/14Model Scale=SO, Patch Size=14, Zero-shot=true2026.0426.8
MERUBackbone=ViT-B/16, Zero-shot=true2026.0326.05
HyCoCLIPBackbone=ViT-B/16, Zero-shot=true2026.0326.03
ReCoTraining-free?=true, Encoder=ViT-B/162024.1125.1
RecoVenue=NeurIPS'222025.1225.1
ReCoLogits Model=CLIP ViT-B/16, Paradigm=M.M.2026.0425.1
MaskCLIPLogits Model=CLIP ViT-L/14, Paradigm=I.T.2026.0424.8
MaskCLIPBackbone=ViT-L/14, Zero-shot=true2025.1223.3