List your company
ResearchFormerly WizWand

Open-vocabulary Semantic Segmentation on PASCAL-Context PC-459

27mIoUESC-Net
4.32810.21416.121.986Nov 22, 2024Feb 18, 2025May 18, 2025Aug 15, 2025Nov 12, 2025Feb 9, 2026May 9, 2026
Updated 5mo ago

Evaluation results

MethodLinks
ESC-NetVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1127
CAT-SegVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1123.8
SEDVLM=ConvNeXt-L, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1122.6
MAFT+VLM=ConvNeXt-L, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1121.6
ESC-NetVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1121.1
EBSegVLM=CLIP ViT-L/14, Additional Backbone=SAM ViT-B, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1121
CAT-SegVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1119
HyRoVLM=CLIP ViT-B/16, Fine-tuning Space=H2026.0518.9
SEDVLM=ConvNeXt-B, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1118.6
SEDVLM=CLIP ConvNeXt-B, Fine-tuning Space=E2026.0518.6
HyperCLIPVLM=CLIP ViT-B/16, Fine-tuning Space=H2026.0518.2
EBSegVLM=CLIP ViT-B/16, Additional Backbone=SAM ViT-B, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1117.3
SCANVLM=CLIP ViT-L/14, Additional Backbone=Swin-B, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1116.7
MAFTVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1116.2
SANVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1115.7
USEVLM=CLIP ViT-L/14, Additional Backbone=DINOv2, SAM, Training Dataset=COCO-Stuff, Additional Dataset=true2024.1115
ODISEVLM=CLIP ViT-L/14, Additional Backbone=Stable Diffusion, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1114.5
SCANVLM=CLIP ViT-B/16, Additional Backbone=Swin-B, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1113.2
FC-CLIPVLM=ConvNeXt-L, Training Dataset=COCO Panoptic, Additional Dataset=false2024.1112.7
SANVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff, Additional Dataset=false2024.1112.6
SANVLM=CLIP ViT-B/16, Additional Backbone=Side Adapter, Fine-tuning Space=E2026.0512.6
OVSegVLM=CLIP ViT-L/14, Additional Backbone=Swin-B, Training Dataset=COCO-Stuff, Additional Dataset=true2024.1112.4
OpenSegVLM=ALIGN, Additional Backbone=EfficientNet-B7, Training Dataset=COCO Panoptic, Additional Dataset=true2024.1111.5
OVSegVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101c, Training Dataset=COCO-Stuff, Additional Dataset=true2024.1111
OVSegVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101c, Fine-tuning Space=E2026.0511
DeOPVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101c, Training Dataset=COCO-Stuff-156, Additional Dataset=false2024.119.4
ZegFormerVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101, Training Dataset=COCO-Stuff-156, Additional Dataset=false2024.119.1
ZegFormerVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101, Fine-tuning Space=E2026.059.1
OpenSegVLM=ALIGN, Additional Backbone=ResNet-101, Training Dataset=COCO Panoptic, Additional Dataset=true2024.117.9
OpenSegVLM=ALIGN, Additional Backbone=ResNet-101, Fine-tuning Space=E2026.057.9
LSeg+VLM=ALIGN, Additional Backbone=ResNet-101, Training Dataset=COCO-Stuff, Additional Dataset=false2024.115.2