Image-Text Retrieval on Retrieval benchmarks (test)
67.7Avg Retrieval PerfFastViTHD
Evaluation Results
| Method | Links | |
|---|---|---|
| FastViTHDEncoder Size(M)=125, Input Res.=224, Latency Enc.(ms)=6.8, Hardware=M1 Macbook Pro2024.12 | 67.7 | |
| ConvNeXt-LEncoder Size(M)=200, Input Res.=320, Latency Enc.(ms)=34.4, Hardware=M1 Macbook Pro2024.12 | 64.8 | |
| ViT-L/14Encoder Size(M)=304, Input Res.=224, Latency Enc.(ms)=47.2, Hardware=M1 Macbook Pro2024.12 | 60.8 | |
| ViTamin-LEncoder Size(M)=333, Input Res.=224, Latency Enc.(ms)=38.1, Hardware=M1 Macbook Pro2024.12 | 60.3 |