List your company

Image-to-image retrieval on Caltech

93mAPPCA←
64.29671.74879.286.652Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026

Evaluation results

MethodLinks
PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.0393
IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0391.6
PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0391.2
OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.0390.7
OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.0390.5
PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.0389.5
OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.0389.2
Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0389.1
OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0388.9
IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0387.6
OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.0387.3
OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.0387.3
OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0387.2
IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0387
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.0385.8
Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0385.7
IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0385
OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.0383.8
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.0383.5
PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.0383.3
Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0383.2
IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0380.8
Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0380.6
OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.0379.9
OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.0379.9
OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.0377.7
Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0377.1
PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0370.7
OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0367.6
OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0365.4