List your company

Image-to-image retrieval on UCF101 (mAP)

70.6mAPOriginal
38.98447.19255.463.608Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026

Evaluation results

MethodLinks
OriginalBackbone=DINOv3, ViT=L/16, Similarity=⟨I, I⟩2026.0370.6
PCA←Backbone=CLIP, ViT=L/14, Similarity=⟨I←, I←⟩2026.0366.8
PCA←Backbone=SigLIP2, ViT=B/16, Similarity=⟨I←, I←⟩2026.0363
OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.0363
OTIBackbone=CLIP, ViT=L/14, Similarity=⟨T, I⟩2026.0362.8
OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.0362.8
IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0362.1
IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0361.9
PCA←Backbone=SigLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0360.3
Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.0360.3
Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.0360
OriginalBackbone=CLIP, ViT=L/14, Similarity=⟨I, I⟩2026.0359.5
OriginalBackbone=SigLIP2, ViT=B/16, Similarity=⟨I, I⟩2026.0359.2
OriginalBackbone=SigLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0356.9
IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0355.4
OTIBackbone=SigLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0354.9
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.0354.1
IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0353.4
PCA←Backbone=CLIP, ViT=B/32, Similarity=⟨I←, I←⟩2026.0353.3
Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.0352.9
OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.0352.6
Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.0349.8
OTIBackbone=CLIP, ViT=B/32, Similarity=⟨T, I⟩2026.0348.6
OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.0348.6
IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0348.4
Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.0347.1
OriginalBackbone=CLIP, ViT=B/32, Similarity=⟨I, I⟩2026.0346.2
PCA←Backbone=SLIP, ViT=B/16, Similarity=⟨I←, I←⟩2026.0342.4
OTIBackbone=SLIP, ViT=B/16, Similarity=⟨T, I⟩2026.0340.6
OriginalBackbone=SLIP, ViT=B/16, Similarity=⟨I, I⟩2026.0340.2