List your company

Image-to-image retrieval on Flowers

99.4mAPOriginal
60.50470.60280.790.798Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026

Evaluation results

MethodLinks
OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.0399.4
PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.0393.2
PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0392
OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0389.7
OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.0389.3
PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.0388.9
IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0388.2
IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0388
OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0387.5
OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.0387.2
OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.0386
OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.0386
IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0385.8
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.0385.2
Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0385
Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0384.6
OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.0384.2
Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0384
IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0377.4
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.0372.8
PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0372.5
Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0370.8
PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.0370.3
IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0366.5
OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0365.7
OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0365.1
OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.0362.6
OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.0362.6
OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.0362.5
Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0362