List your company
ResearchFormerly WizWand

Semantic Segmentation on PASCAL Context without background class 59

38.6mIoUTagAlign
8.64816.42424.231.976Dec 1, 2022Apr 2, 2023Aug 2, 2023Dec 2, 2023Apr 2, 2024Aug 2, 2024Dec 2, 2024
Updated 8mo ago

Evaluation results

MethodLinks
TagAlignPost-processing=false, Training Datasets=CC12M, Zero-shot evaluation=true2023.1238.6
TagAlignPost-processing=true, Training Datasets=CC12M, Zero-shot evaluation=true2023.1235.1
SCLIPData Size=400M, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.1234.2
TCLEvaluation Mode=Zero-shot2022.1233.9
TCLPost-processing=false, Training Datasets=CC3&12M, Zero-shot evaluation=true2023.1233.9
COSMOS w/ SCLIPData Size=30M, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.1233.7
SILC-CData Size=10B, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.1231.6
TCLPost-processing=true, Training Datasets=CC3&12M, Zero-shot evaluation=true2023.1230.3
MaskCLIPRefinement=With heuristic refinement2022.1226.4
Dong et al.Post-processing=true, Training Datasets=LAION-20M, Zero-shot evaluation=true2023.1226.4
MaskCLIPData Size=400M, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.1226.4
Dong et al.Post-processing=false, Training Datasets=LAION-20M, Zero-shot evaluation=true2023.1225.3
SegCLIPPost-processing=true, Training Datasets=CC12M+COCO, Zero-shot evaluation=true2023.1224.8
ReCoPost-processing=false, Training Datasets=ImageNet1K, Zero-shot evaluation=true2023.1224.7
GroupViTPost-processing=false, Training Datasets=CC12M+YFCC, Zero-shot evaluation=true2023.1223.8
GroupViT (RedCaps)Training Data=RedCaps + CC12M2022.1223.4
MaskCLIP (Baseline)Refinement=None2022.1223.3
ReCoEvaluation Mode=Zero-shot2022.1222.3
ReCoPost-processing=true, Training Datasets=ImageNet1K, Zero-shot evaluation=true2023.1222.3
GroupViT (YFCC)Training Data=YFCC + CC12M2022.1220.8
GroupViTPost-processing=true, Training Datasets=CC12M+YFCC, Zero-shot evaluation=true2023.1220.8
OVSegmentorPost-processing=true, Training Datasets=CC12M*, Zero-shot evaluation=true2023.1219.2
COSMOSData Size=30M, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.1215.7
OpenCLIPData Size=1B, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.1212.6
CLIPData Size=400M, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.1211.1
OpenCLIPData Size=2B, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.1210.2
OpenCLIPData Size=400M, Zero-shot=true, Vision Encoder Architecture=ViT-B/162024.129.8