Cross-modal Retrieval on UCM (test)
28.57R@1 (I2T)FBCLM
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| FBCLMTraining Dataset=UCM, Training Samples=2,100, Date=May 2022, Image Backbone Name=Resnet-18, Text Backbone Name=BERT2023.06 | 28.57 | 63.81 | 82.86 | 27.33 | 72.67 | 94.38 | 61.6 | |
| RemoteCLIPTraining Dataset=RET-3 + DET-10 + SEG-4, Training Samples=165,745, Date=2023, Image Backbone Name=ViT-B-32, Image Backbone Params=87, Text Backbone Name=Transformer, Text Backbone Params=63, Total Params=1512023.06 | 20.48 | 59.85 | 83.33 | 18.67 | 61.52 | 94.29 | 56.36 | |
| CLIP-CLTraining Dataset=RET-3, Training Samples=13,713, Image Backbone Name=ViT-B-32, Image Backbone Params=88, Text Backbone Name=Transformer, Text Backbone Params=64, Total Params=1512023.06 | 20 | 55.24 | 80.95 | 18.19 | 64.86 | 92.38 | 55.27 | |
| RemoteCLIPTraining Dataset=RET-3 + DET-10 + SEG-4, Training Samples=165,745, Date=Jun 2023, Image Backbone Name=ViT-L-14, Image Backbone Params=304, Text Backbone Name=Transformer, Text Backbone Params=124, Total Params=4282023.06 | 19.05 | 54.29 | 80.95 | 17.71 | 62.19 | 93.9 | 54.68 | |
| Rahhal et al.Training Dataset=UCM, Training Samples=2,100, Date=Oct 2022, Image Backbone Name=ViT-B-32, Image Backbone Params=87, Text Backbone Name=Transformer, Text Backbone Params=63, Total Params=1512023.06 | 19.04 | 53.33 | 77.61 | 19.33 | 64 | 91.42 | 54.12 | |
| LW-MRC-uTraining Dataset=UCM, Training Samples=2,100, Date=Dec 2020, Image Backbone Name=Big Transfer, Text Backbone Name=Bi-LSTM2023.06 | 18.1 | 47.14 | 63.81 | 13.14 | 50.38 | 79.52 | 45.35 | |
| AMFMNTraining Dataset=UCM, Training Samples=2,100, Date=Aug 2020, Image Backbone Name=ResNet-50, Text Backbone Name=GloVe fasText2023.06 | 16.67 | 45.71 | 68.57 | 12.86 | 53.24 | 79.43 | 46.08 | |
| CLIP-CLTraining Dataset=RET-3, Training Samples=13,713, Image Backbone Name=ResNet-50, Image Backbone Params=38, Text Backbone Name=Transformer, Text Backbone Params=64, Total Params=1022023.06 | 14.29 | 44.76 | 72.86 | 13.52 | 53.71 | 82.1 | 46.87 | |
| RemoteCLIPTraining Dataset=RET-3 + DET-10 + SEG-4, Training Samples=165,745, Date=2023, Image Backbone Name=ResNet-50, Image Backbone Params=38, Text Backbone Name=Transformer, Text Backbone Params=64, Total Params=1022023.06 | 13.33 | 50.48 | 74.76 | 15.24 | 57.14 | 84.57 | 49.25 | |
| SCANTraining Dataset=UCM, Training Samples=2,100, Date=Mar 2018, Image Backbone Name=ResNet-101, Text Backbone Name=GRU2023.06 | 12.85 | 47.14 | 69.52 | 12.48 | 46.86 | 71.71 | 43.43 | |
| VSE++Training Dataset=UCM, Training Samples=2,100, Date=Jul 2017, Image Backbone Name=VGG19, Text Backbone Name=GRU2023.06 | 12.38 | 44.76 | 65.71 | 10.1 | 31.8 | 56.85 | 36.93 | |
| MTFNTraining Dataset=UCM, Training Samples=2,100, Date=Aug 2019, Image Backbone Name=ResNet, Text Backbone Name=GRU2023.06 | 10.47 | 47.62 | 64.29 | 14.19 | 52.38 | 78.95 | 44.65 |