List your company

Image-to-image retrieval on Pets

82.3mAPOriginal
15.2232.63550.0567.465Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026

Evaluation results

MethodLinks
OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.0382.3
PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0368.5
IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0368.2
PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.0367.8
OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0364.2
IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0363.5
OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.0362.9
PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.0362.7
IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0357.8
Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0357.1
OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.0356.6
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.0356.5
OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0356.4
OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.0356
OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.0356
IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0350.7
Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0350.4
PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.0347.7
Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0347.3
OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.0347.2
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.0342.9
IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0340.8
OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.0337.5
OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.0337.5
Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0336.3
OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.0331.2
Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0330.5
PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0323.1
OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0319.3
OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0317.8