List your company
ResearchFormerly WizWand

Image-to-image retrieval on Aircraft

46.3mAPPCA←
7.50817.57927.6537.721Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026
Updated 7mo ago

Evaluation results

MethodLinks
PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.0346.3
PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0340.9
OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.0340.7
OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.0339.8
OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0337.9
OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0337.6
IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0334.9
OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.0332.7
Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0331.7
PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.0328.7
IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0328.2
OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.0327.1
OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.0327.1
OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.0325.8
Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0325.8
IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0323.5
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.0323.4
Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0323.1
IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0320.5
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.0320.1
Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0319
PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.0316.1
IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0314.9
OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.0314.5
Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0314.5
OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.0314.4
OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.0314.4
PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0310.3
OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.039.1
OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.039