List your company

Semantic Segmentation on 8 Dataset Aggregate (VOC, Context, Object, VOC20, Context59, Stuff, City, ADE)

44.4mIoU (Average)ProxyCLIP
3.63214.21624.835.384Aug 9, 2024

Evaluation results

MethodLinks
ProxyCLIPBackbone=OpenCLIP-ViT-H/14, Training Strategy=Zero-shot2024.0844.4
ProxyCLIPBackbone=CLIP-ViT-L/14, Training Strategy=Zero-shot2024.0843
ProxyCLIPBackbone=CLIP-ViT-B/16, Training Strategy=Zero-shot2024.0842.3
CLIP-DINOiserTraining Strategy=Training-based2024.0840.3
SCLIPBackbone=CLIP-ViT-B/16, Training Strategy=Zero-shot2024.0838.2
TCLTraining Strategy=Training-based2024.0833.1
SCLIPBackbone=OpenCLIP-ViT-H/14, Training Strategy=Zero-shot2024.0829.1
SCLIPBackbone=CLIP-ViT-L/14, Training Strategy=Zero-shot2024.0829
MaskCLIP+Backbone=CLIP-ViT-B/16, Training Strategy=Zero-shot2024.0827.9
GroupViTTraining Strategy=Training-based2024.0827.7
ReCo+Backbone=CLIP-ViT-B/16, Training Strategy=Zero-shot2024.0823.5
MaskCLIPBackbone=OpenCLIP-ViT-H/14, Training Strategy=Zero-shot2024.0819.3
MaskCLIPBackbone=CLIP-ViT-L/14, Training Strategy=Zero-shot2024.0813.9
CLIPBackbone=CLIP-ViT-B/16, Training Strategy=Zero-shot2024.0811.7
OpenCLIPBackbone=OpenCLIP-ViT-H/14, Training Strategy=Zero-shot2024.087.1
CLIPBackbone=CLIP-ViT-L/14, Training Strategy=Zero-shot2024.085.2