List your company

Fine-grained captioning on Dream1k

29.5F1 ScoreFluxViT-L
24.40425.72727.0528.373Mar 18, 2025

Evaluation results

MethodLinks
FluxViT-LEncoder=FluxViT-L, #Tokens=2048, Token Optimization=true, Evaluation Protocol=linear probe2025.0329.5
SigLIP336-LEncoder=SigLIP336-L, #Tokens=8x576, Token Optimization=false, Evaluation Protocol=linear probe2025.0329.2
FluxViT-LEncoder=FluxViT-L, #Tokens=8x256, Token Optimization=false, Evaluation Protocol=linear probe2025.0329
InternVideo2-LEncoder=InternVideo2-L, #Tokens=8x224, Token Optimization=false, Evaluation Protocol=linear probe2025.0328.7
FluxViT-LEncoder=FluxViT-L, #Tokens=1024, Token Optimization=true, Evaluation Protocol=linear probe2025.0328.5
Clip-LEncoder=Clip-L, #Tokens=8x256, Token Optimization=false, Evaluation Protocol=linear probe2025.0328.4
FluxViT-LEncoder=FluxViT-L, #Tokens=4x256, Token Optimization=false, Evaluation Protocol=linear probe2025.0327.9
FluxViT-LEncoder=FluxViT-L, #Tokens=512, Token Optimization=true, Evaluation Protocol=linear probe2025.0327.5
FluxViT-LEncoder=FluxViT-L, #Tokens=2x256, Token Optimization=false, Evaluation Protocol=linear probe2025.0325.6
SigLIP336-LEncoder=SigLIP336-L, #Tokens=4x576, Token Optimization=false, Evaluation Protocol=linear probe2025.0325.4
UMT-LEncoder=UMT-L, #Tokens=4x256, Token Optimization=false, Evaluation Protocol=linear probe2025.0324.6