List your company

Image-to-image retrieval on Cars

80.2mAPPCA←
1.88822.21942.5562.881Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026

Evaluation results

MethodLinks
PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.0380.2
PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0377.2
OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0371.8
OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.0370.8
OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.0368.6
OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0365.7
IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0362.3
IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0360.7
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.0360.5
OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.0360.2
PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.0357.2
IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0356.4
Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0355.8
Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0353.4
OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.0350.5
OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.0350.5
OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.0343.8
Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0343.3
IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0341.2
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.0337.2
PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.0334.6
Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0331
IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0330
OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.0328
OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.0328
OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.0324.9
Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0324.6
PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.036.2
OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.035
OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.034.9