Text Retrieval on xFlickr&CO
63.79Recall@1ToMCLIP(Lta)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ToMCLIP(Lta)Setting=Full data (2M samples), Image Encoder=ViT-B/16+2025.10 | 63.79 | 86.21 | 91.98 | |
| ToMCLIP(Ldm)Setting=Full data (2M samples), Image Encoder=ViT-B/16+2025.10 | 62.95 | 85.67 | 91.14 | |
| MCLIPSetting=Full data (2M samples), Image Encoder=ViT-B/16+2025.10 | 62.82 | 85.47 | 91.32 | |
| ToMCLIPSetting=Full data (2M samples), Image Encoder=ViT-B/16+2025.10 | 62.19 | 85.09 | 90.84 | |
| ToMCLIP(Ldm)Setting=Low resource (1% subset), Image Encoder=ViT-B/16+2025.10 | 57.99 | 83.84 | 90.63 | |
| ToMCLIPSetting=Low resource (1% subset), Image Encoder=ViT-B/16+2025.10 | 57.57 | 83.39 | 90.61 | |
| ToMCLIP(Lta)Setting=Low resource (1% subset), Image Encoder=ViT-B/16+2025.10 | 57.33 | 83.26 | 90.27 | |
| MCLIPSetting=Low resource (1% subset), Image Encoder=ViT-B/16+2025.10 | 56.73 | 83.33 | 90.34 | |
| CLIPSetting=Low resource (1% subset), Image Encoder=ViT-B/16+2025.10 | 18.91 | 31.46 | 36.59 | |
| CLIPSetting=Full data (2M samples), Image Encoder=ViT-B/16+2025.10 | 18.91 | 31.46 | 36.59 |