Image-to-image retrieval on Flowers
99.4mAPOriginal
Evaluation Results
| Method | Links | |
|---|---|---|
| OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.03 | 99.4 | |
| PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.03 | 93.2 | |
| PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.03 | 92 | |
| OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.03 | 89.7 | |
| OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.03 | 89.3 | |
| PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.03 | 88.9 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.03 | 88.2 | |
| IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.03 | 88 | |
| OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.03 | 87.5 | |
| OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.03 | 87.2 | |
| OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.03 | 86 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.03 | 86 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.03 | 85.8 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.03 | 85.2 | |
| Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.03 | 85 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.03 | 84.6 | |
| OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.03 | 84.2 | |
| Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.03 | 84 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.03 | 77.4 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.03 | 72.8 | |
| PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.03 | 72.5 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.03 | 70.8 | |
| PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.03 | 70.3 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.03 | 66.5 | |
| OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.03 | 65.7 | |
| OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.03 | 65.1 | |
| OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.03 | 62.6 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.03 | 62.6 | |
| OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.03 | 62.5 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.03 | 62 |