Image-to-image retrieval on CUB
53mAPIsoCLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| IsoCLIPIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.03 | 53 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.03 | 52.2 | |
| OTI (I→T)Intra-modal=false, Backbone=PE-Core-B-16, Latency (ms)=3252 ± 352026.03 | 51.5 | |
| Image-ImageIntra-modal=true, Backbone=PE-Core-B-16, Latency (ms)=8 ± 12026.03 | 48.9 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-L/14, Latency (ms)=1872 ± 912026.03 | 47.1 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.03 | 45.9 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/16-open, Latency (ms)=1836 ± 832026.03 | 45.1 | |
| Image-ImageIntra-modal=true, Backbone=ViT-L/14, Latency (ms)=11 ± 12026.03 | 43 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/16-open, Latency (ms)=6 ± 12026.03 | 42.8 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.03 | 38.6 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/16, Latency (ms)=1856 ± 562026.03 | 33.9 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/16, Latency (ms)=6 ± 12026.03 | 31.6 | |
| IsoCLIPIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.03 | 27 | |
| OTI (I→T)Intra-modal=false, Backbone=ViT-B/32, Latency (ms)=1879 ± 352026.03 | 24.6 | |
| Image-ImageIntra-modal=true, Backbone=ViT-B/32, Latency (ms)=7 ± 12026.03 | 22.9 |