List your company

Image-to-image Retrieval on DTD

44.9mAPOriginal
27.42831.96436.541.036Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026

Evaluation results

MethodLinks
OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.0344.9
PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0344.2
PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.0344.1
OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.0343.5
OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0343.3
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.0343.1
IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0343.1
IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0342.5
PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.0339.9
Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0339.9
OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0339.8
IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0339
Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0339
OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.0338.6
OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.0337.7
OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.0337.7
IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0336
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.0335.1
Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0334.1
PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.0334
OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.0333.9
PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0332.2
OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.0331.9
OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.0331.9
IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0330.9
Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0330.7
OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0330.5
OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0329.7
OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.0328.3
Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0328.1