Text-to-Image Retrieval on COCO 1K (test)
73.4R@1Ours†
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ours†Backbone=ResNeXt-101 + BERT, CA (Cross-Attention)=false, Ensemble=true2022.11 | 73.4 | 94.5 | 97.8 | 549.9 | |
| VSE∞†Backbone=ResNeXt-101 + BERT, CA (Cross-Attention)=false, Ensemble=true2022.11 | 73.1 | 94.3 | 97.7 | 548.1 | |
| OursBackbone=ResNeXt-101 + BERT, CA (Cross-Attention)=false, Ensemble=false2022.11 | 72.4 | 94 | 97.6 | 547.5 | |
| VSE∞Backbone=ResNeXt-101 + BERT, CA (Cross-Attention)=false, Ensemble=false2022.11 | 72 | 93.9 | 97.5 | 545.4 | |
| Ours†Backbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=false, Ensemble=true2022.11 | 64.7 | 91.4 | 96.2 | 528 | |
| NAAFBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=true2022.11 | 64.1 | 90.7 | 96.5 | 527.2 | |
| OursBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.11 | 63.6 | 90.7 | 95.7 | 524.6 | |
| SGRAFBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=true2022.11 | 63.2 | 90.7 | 96.1 | 524.3 | |
| VSRNBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=false, Ensemble=true2022.11 | 62.8 | 89.7 | 95.1 | 516.8 | |
| IMRAMBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=true2022.11 | 61.7 | 89.1 | 95 | 516.6 | |
| VSE∞Backbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.11 | 61.7 | 90.3 | 95.6 | 520.8 | |
| CAANBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=false2022.11 | 61.3 | 89.7 | 95.2 | 515.6 | |
| SCANBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=true2022.11 | 58.8 | 88.4 | 94.8 | 507.9 | |
| OursBackbone=ResNet-152 + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.11 | 56 | 85.8 | 93.3 | 493.2 | |
| PVSEBackbone=ResNet-152 + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.11 | 55.2 | 86.5 | 93.7 | 492.8 | |
| PCMEBackbone=ResNet-152 + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.11 | 54.6 | — | — | — | |
| VSE++Backbone=ResNet-152 + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.11 | 52 | 84.3 | 92 | 478.6 |