Cross-modal Retrieval on Flickr30k (test)
82.3Image-to-text Recall@1RCAR
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| RCARBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=true2024.04 | 82.3 | 96 | 98.4 | 62.6 | 85.8 | 91.1 | 516.2 | |
| DSMDBackbone=ViT, BERT, Visual Embed=Image, Ensemble=false2024.04 | 82 | 95.5 | 97.7 | 68.4 | 90.8 | 94.4 | 528.8 | |
| GPOBackbone=BUTD, BERT, Visual Embed=Region, Ensemble=false2024.04 | 81.7 | 95.4 | 97.6 | 61.4 | 85.9 | 91.5 | 513.5 | |
| DIMEBackbone=BUTD, BERT, Visual Embed=Region, Ensemble=true2024.04 | 81 | 95.9 | 98.4 | 63.6 | 88.1 | 93 | 520 | |
| VSRN++Backbone=BUTD, BERT, Visual Embed=Region, Ensemble=false2024.04 | 79.2 | 96.4 | 97.5 | 60.6 | 85.6 | 91.4 | 510.7 | |
| CAMERABackbone=BUTD, BERT, Visual Embed=Region, Ensemble=true2024.04 | 78 | 95.1 | 97.9 | 60.3 | 85.9 | 91.7 | 508.9 | |
| SGRAFBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=false2024.04 | 77.8 | 94.1 | 97.4 | 58.5 | 83 | 88.8 | 499.6 | |
| ADAPTBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=true2024.04 | 76.6 | 95.4 | 97.6 | 60.7 | 86.6 | 92 | 508.9 | |
| GSMNBackbone=Faster RCNN, GRU, Visual Embed=Region, Ensemble=true2024.04 | 76.4 | 94.3 | 97.3 | 57.4 | 82.3 | 89 | 496.7 | |
| WCGLBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=false2024.04 | 74.8 | 93.3 | 96.8 | 54.8 | 80.6 | 87.5 | 487.8 | |
| SHANBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=true2024.04 | 74.6 | 93.5 | 96.9 | 55.3 | 81.3 | 88.4 | 490 | |
| MMCABackbone=BUTD, BERT, Visual Embed=Region, Ensemble=false2024.04 | 74.2 | 92.8 | 96.4 | 54.8 | 81.4 | 87.8 | 487.4 | |
| IMRAMBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=false2024.04 | 74.1 | 93 | 96.6 | 53.9 | 79.4 | 87.2 | 484.2 | |
| VSRNBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=true2024.04 | 71.3 | 90.6 | 96 | 54.7 | 81.8 | 88.2 | 482.6 | |
| CAANBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=false2024.04 | 70.1 | 91.6 | 97.2 | 52.8 | 79 | 87.9 | 478.6 | |
| BFANBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=true2024.04 | 68.1 | 91.4 | — | 50.8 | 78.4 | — | — | |
| SCANBackbone=BUTD, GRU, Visual Embed=Region, Ensemble=true2024.04 | 67.4 | 90.3 | 95.8 | 48.6 | 77.7 | 85.2 | 465 | |
| FedAFDData setting=Non-IID, Evaluation site=Clients, #rounds=202026.03 | 32.48 | — | — | 25.68 | — | — | — | |
| FedETData setting=Non-IID, Evaluation site=Clients, #rounds=272026.03 | 22.63 | — | — | 18.22 | — | — | — | |
| LOCALData setting=Non-IID, Evaluation site=Clients, #rounds=292026.03 | 22.33 | — | — | 18.44 | — | — | — | |
| FedMKDData setting=Non-IID, Evaluation site=Clients, #rounds=212026.03 | 22.33 | — | — | 18.37 | — | — | — | |
| FedDFAData setting=Non-IID, Evaluation site=Clients, #rounds=262026.03 | 19.68 | — | — | 17.13 | — | — | — | |
| FedMDData setting=Non-IID, Evaluation site=Clients, #rounds=252026.03 | 19.13 | — | — | 15.63 | — | — | — | |
| FedGEMSData setting=Non-IID, Evaluation site=Clients, #rounds=272026.03 | 18.93 | — | — | 16.05 | — | — | — | |
| CreamFLData setting=Non-IID, Evaluation site=Clients, #rounds=212026.03 | 18.38 | — | — | 15.49 | — | — | — |