Image-to-image retrieval on Cars
80.2mAPPCA←
Evaluation Results
| Method | Links | |
|---|---|---|
| PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.03 | 80.2 | |
| PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.03 | 77.2 | |
| OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.03 | 71.8 | |
| OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.03 | 70.8 | |
| OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.03 | 68.6 | |
| OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.03 | 65.7 | |
| IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.03 | 62.3 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.03 | 60.7 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.03 | 60.5 | |
| OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.03 | 60.2 | |
| PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.03 | 57.2 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.03 | 56.4 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.03 | 55.8 | |
| Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.03 | 53.4 | |
| OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.03 | 50.5 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.03 | 50.5 | |
| OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.03 | 43.8 | |
| Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.03 | 43.3 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.03 | 41.2 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.03 | 37.2 | |
| PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.03 | 34.6 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.03 | 31 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.03 | 30 | |
| OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.03 | 28 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.03 | 28 | |
| OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.03 | 24.9 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.03 | 24.6 | |
| PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.03 | 6.2 | |
| OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.03 | 5 | |
| OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.03 | 4.9 |