List your company

Image-to-image retrieval on SUN397

50.1mAPOriginal
25.1431.6238.144.58Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026

Evaluation results

MethodLinks
OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.0350.1
PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.0348.9
PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0346.9
PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.0346
IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0345.2
OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.0344.9
Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0343.9
OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0343.6
OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.0343.5
OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.0343.5
OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.0343
OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0342.8
IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0341
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.0340.8
PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.0340
Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0339.5
IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0339.3
OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.0339.2
Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0339.1
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.0338.7
IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0338.5
IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0336.4
OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.0336.3
OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.0336.3
Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0335.9
OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.0334.6
Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0334.3
PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0330.7
OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0326.4
OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0326.1